├── .gitattributes ├── .gitignore ├── CHANGES.txt ├── HEADER.txt ├── KEYS ├── LICENSE.txt ├── NOTICE.txt ├── README-apache.md ├── README.md ├── assembly.xml ├── pom.xml ├── tika-app ├── pom.xml └── src │ ├── main │ ├── appended-resources │ │ └── META-INF │ │ │ └── LICENSE │ ├── assembly │ │ └── standalone.xml │ ├── java │ │ └── org │ │ │ └── apache │ │ │ └── tika │ │ │ ├── batch │ │ │ ├── DigestingAutoDetectParserFactory.java │ │ │ └── builders │ │ │ │ └── AppParserFactoryBuilder.java │ │ │ ├── cli │ │ │ ├── BatchCommandLineBuilder.java │ │ │ └── TikaCLI.java │ │ │ └── gui │ │ │ ├── ParsingTransferHandler.java │ │ │ └── TikaGUI.java │ ├── resources-filtered │ │ └── org │ │ │ └── apache │ │ │ └── tika │ │ │ └── gui │ │ │ ├── about.html │ │ │ └── welcome.html │ └── resources │ │ ├── log4j.properties │ │ ├── log4j_batch_process.properties │ │ ├── org │ │ └── apache │ │ │ └── tika │ │ │ └── gui │ │ │ └── tika.png │ │ └── tika-app-batch-config.xml │ └── test │ ├── java │ └── org │ │ └── apache │ │ └── tika │ │ ├── cli │ │ ├── TikaCLIBatchCommandLineTest.java │ │ ├── TikaCLIBatchIntegrationTest.java │ │ └── TikaCLITest.java │ │ └── extractor │ │ └── TestEmbeddedDocumentUtil.java │ └── resources │ ├── log4j_batch_process_test.properties │ └── test-data │ ├── TIKA-2389-ignore-init-problems.xml │ ├── alice.cli.test │ ├── bad_xml.xml │ ├── coffee.xls │ ├── test-documents.tgz │ ├── testJsonMultipleInts.html │ ├── testMultipleSheets.numbers │ ├── testPDF_childAttachments.pdf │ ├── testWithSubdirs.zip │ ├── testZip_absolutePath.zip │ ├── testZip_overlappingNames.zip │ ├── testZip_relative.zip │ ├── testZip_zeroByte.zip │ ├── test_recursive_embedded.docx │ ├── tika-config1.xml │ ├── tika-config2.xml │ └── welsh_corpus.txt ├── tika-batch ├── pom.xml └── src │ ├── main │ ├── java │ │ ├── org │ │ │ └── apache │ │ │ │ └── tika │ │ │ │ ├── batch │ │ │ │ ├── AutoDetectParserFactory.java │ │ │ │ ├── BatchNoRestartError.java │ │ │ │ ├── BatchProcess.java │ │ │ │ ├── BatchProcessDriverCLI.java │ │ │ │ ├── ConsumersManager.java │ │ │ │ ├── FileConsumerFutureResult.java │ │ │ │ ├── FileResource.java │ │ │ │ ├── FileResourceConsumer.java │ │ │ │ ├── FileResourceCrawler.java │ │ │ │ ├── FileResourceCrawlerFutureResult.java │ │ │ │ ├── FileStarted.java │ │ │ │ ├── IFileProcessorFutureResult.java │ │ │ │ ├── Interrupter.java │ │ │ │ ├── InterrupterFutureResult.java │ │ │ │ ├── OutputStreamFactory.java │ │ │ │ ├── ParallelFileProcessingResult.java │ │ │ │ ├── ParserFactory.java │ │ │ │ ├── PoisonFileResource.java │ │ │ │ ├── StatusReporter.java │ │ │ │ ├── StatusReporterFutureResult.java │ │ │ │ ├── builders │ │ │ │ │ ├── AbstractConsumersBuilder.java │ │ │ │ │ ├── BatchProcessBuilder.java │ │ │ │ │ ├── CommandLineParserBuilder.java │ │ │ │ │ ├── DefaultContentHandlerFactoryBuilder.java │ │ │ │ │ ├── IContentHandlerFactoryBuilder.java │ │ │ │ │ ├── ICrawlerBuilder.java │ │ │ │ │ ├── IParserFactoryBuilder.java │ │ │ │ │ ├── InterrupterBuilder.java │ │ │ │ │ ├── ObjectFromDOMAndQueueBuilder.java │ │ │ │ │ ├── ObjectFromDOMBuilder.java │ │ │ │ │ ├── ParserFactoryBuilder.java │ │ │ │ │ ├── ReporterBuilder.java │ │ │ │ │ ├── SimpleLogReporterBuilder.java │ │ │ │ │ └── StatusReporterBuilder.java │ │ │ │ └── fs │ │ │ │ │ ├── AbstractFSConsumer.java │ │ │ │ │ ├── BasicTikaFSConsumer.java │ │ │ │ │ ├── FSBatchProcessCLI.java │ │ │ │ │ ├── FSConsumersManager.java │ │ │ │ │ ├── FSDirectoryCrawler.java │ │ │ │ │ ├── FSDocumentSelector.java │ │ │ │ │ ├── FSFileResource.java │ │ │ │ │ ├── FSListCrawler.java │ │ │ │ │ ├── FSOutputStreamFactory.java │ │ │ │ │ ├── FSProperties.java │ │ │ │ │ ├── FSUtil.java │ │ │ │ │ ├── RecursiveParserWrapperFSConsumer.java │ │ │ │ │ ├── StreamOutRPWFSConsumer.java │ │ │ │ │ ├── builders │ │ │ │ │ ├── BasicTikaFSConsumersBuilder.java │ │ │ │ │ └── FSCrawlerBuilder.java │ │ │ │ │ └── strawman │ │ │ │ │ └── StrawManTikaAppDriver.java │ │ │ │ └── util │ │ │ │ ├── ClassLoaderUtil.java │ │ │ │ ├── DurationFormatUtils.java │ │ │ │ ├── PropsUtil.java │ │ │ │ └── XMLDOMUtil.java │ │ └── overview.html │ └── resources │ │ └── org │ │ └── apache │ │ └── tika │ │ └── batch │ │ └── fs │ │ └── default-tika-batch-config.xml │ └── test │ ├── java │ └── org │ │ └── apache │ │ └── tika │ │ ├── batch │ │ ├── CommandLineParserBuilderTest.java │ │ ├── RecursiveParserWrapperFSConsumerTest.java │ │ ├── fs │ │ │ ├── BatchDriverTest.java │ │ │ ├── BatchProcessTest.java │ │ │ ├── FSBatchTestBase.java │ │ │ ├── FSFileResourceTest.java │ │ │ ├── FSUtilTest.java │ │ │ ├── HandlerBuilderTest.java │ │ │ ├── OutputStreamFactoryTest.java │ │ │ ├── StringStreamGobbler.java │ │ │ └── strawman │ │ │ │ └── StrawmanTest.java │ │ └── mock │ │ │ ├── MockConsumersBuilder.java │ │ │ └── MockConsumersManager.java │ │ └── parser │ │ └── mock │ │ └── MockParserFactory.java │ └── resources │ ├── log4j-on.properties │ ├── log4j.properties │ ├── log4j_process.properties │ ├── test-documents │ ├── embedded_then_npe.xml │ ├── embedded_with_npe.xml │ └── null_pointer.xml │ ├── test-input │ ├── basic │ │ └── test0.xml │ ├── heavy_heavy_hangs │ │ ├── test0_heavy_hang.xml │ │ ├── test1_heavy_hang.xml │ │ ├── test2_heavy_hang.xml │ │ ├── test3_heavy_hang.xml │ │ ├── test4_heavy_hang.xml │ │ ├── test5_heavy_hang.xml │ │ └── test6_ok.xml │ ├── hierarchical │ │ ├── sub1a │ │ │ ├── sub2a │ │ │ │ └── test3.xml │ │ │ └── test2.xml │ │ └── test1.xml │ ├── illegal_xml_chars_in_exception │ │ ├── test0_bad_chars.xml │ │ └── test1_ok.xml │ ├── max_restarts │ │ ├── test0_oom.xml │ │ ├── test1_oom.xml │ │ ├── test2_oom.xml │ │ └── test3_ok.xml │ ├── no_restart │ │ ├── test1_ok.xml │ │ ├── test2_norestart.xml │ │ └── test3_ok.xml │ ├── noisy_parsers │ │ └── test0.xml │ ├── one_heavy_hang │ │ ├── test0_heavy_hang.xml │ │ ├── test1_ok.xml │ │ ├── test2_ok.xml │ │ ├── test3_ok.xml │ │ └── test4_ok.xml │ ├── oom │ │ ├── test0_sleep.xml │ │ ├── test1_heavy_hang.xml │ │ ├── test2_ok.xml │ │ ├── test3_oom.xml │ │ ├── test4_ok.xml │ │ └── test5_ok.xml │ ├── system_exit │ │ ├── test0_system_exit.xml │ │ ├── test1_system_exit.xml │ │ ├── test2_system_exit.xml │ │ ├── test3_ok.xml │ │ ├── test4_ok.xml │ │ └── test5_ok.xml │ ├── thread_interrupt │ │ ├── test0_thread_interrupt.xml │ │ ├── test1_thread_interrupt.xml │ │ ├── test2_thread_interrupt.xml │ │ ├── test3_ok.xml │ │ ├── test4_ok.xml │ │ └── test5_ok.xml │ ├── timeout_after_early_termination │ │ └── test0_sleep.xml │ └── wait_after_early_termination │ │ └── test0_sleep.xml │ ├── testFileList.txt │ ├── tika-batch-config-MockConsumersBuilder.xml │ ├── tika-batch-config-broken.xml │ ├── tika-batch-config-test-suffix-override.xml │ └── tika-batch-config-test.xml ├── tika-bundle ├── pom.xml ├── src │ ├── main │ │ ├── appended-resources │ │ │ └── META-INF │ │ │ │ └── LICENSE │ │ └── resources │ │ │ └── META-INF │ │ │ └── MANIFEST.MF │ └── test │ │ ├── java │ │ └── org │ │ │ └── apache │ │ │ └── tika │ │ │ └── bundle │ │ │ └── BundleIT.java │ │ └── resources │ │ ├── log4j.properties │ │ ├── test-documents.zip │ │ └── testOCR.jpg └── test-bundles.xml ├── tika-core ├── pom.xml └── src │ ├── main │ ├── appended-resources │ │ └── META-INF │ │ │ └── LICENSE │ ├── java │ │ └── org │ │ │ └── apache │ │ │ └── tika │ │ │ ├── Tika.java │ │ │ ├── concurrent │ │ │ ├── ConfigurableThreadPoolExecutor.java │ │ │ └── SimpleThreadPoolExecutor.java │ │ │ ├── config │ │ │ ├── Field.java │ │ │ ├── Initializable.java │ │ │ ├── InitializableProblemHandler.java │ │ │ ├── LoadErrorHandler.java │ │ │ ├── Param.java │ │ │ ├── ParamField.java │ │ │ ├── ServiceLoader.java │ │ │ ├── TikaActivator.java │ │ │ ├── TikaConfig.java │ │ │ ├── TikaConfigSerializer.java │ │ │ └── package-info.java │ │ │ ├── detect │ │ │ ├── AutoDetectReader.java │ │ │ ├── CompositeDetector.java │ │ │ ├── CompositeEncodingDetector.java │ │ │ ├── DefaultDetector.java │ │ │ ├── DefaultEncodingDetector.java │ │ │ ├── DefaultProbDetector.java │ │ │ ├── Detector.java │ │ │ ├── EmptyDetector.java │ │ │ ├── EncodingDetector.java │ │ │ ├── MagicDetector.java │ │ │ ├── NNExampleModelDetector.java │ │ │ ├── NNTrainedModel.java │ │ │ ├── NNTrainedModelBuilder.java │ │ │ ├── NameDetector.java │ │ │ ├── NonDetectingEncodingDetector.java │ │ │ ├── OverrideDetector.java │ │ │ ├── TextDetector.java │ │ │ ├── TextStatistics.java │ │ │ ├── TrainedModel.java │ │ │ ├── TrainedModelDetector.java │ │ │ ├── TypeDetector.java │ │ │ ├── XmlRootExtractor.java │ │ │ ├── ZeroSizeFileDetector.java │ │ │ └── package-info.java │ │ │ ├── embedder │ │ │ ├── Embedder.java │ │ │ └── ExternalEmbedder.java │ │ │ ├── exception │ │ │ ├── AccessPermissionException.java │ │ │ ├── CorruptedFileException.java │ │ │ ├── EncryptedDocumentException.java │ │ │ ├── TikaConfigException.java │ │ │ ├── TikaException.java │ │ │ ├── TikaMemoryLimitException.java │ │ │ ├── UnsupportedFormatException.java │ │ │ ├── ZeroByteFileException.java │ │ │ └── package-info.java │ │ │ ├── extractor │ │ │ ├── ContainerExtractor.java │ │ │ ├── DocumentSelector.java │ │ │ ├── EmbeddedDocumentExtractor.java │ │ │ ├── EmbeddedDocumentUtil.java │ │ │ ├── EmbeddedResourceHandler.java │ │ │ ├── ParserContainerExtractor.java │ │ │ ├── ParsingEmbeddedDocumentExtractor.java │ │ │ └── package-info.java │ │ │ ├── fork │ │ │ ├── ClassLoaderProxy.java │ │ │ ├── ClassLoaderResource.java │ │ │ ├── ContentHandlerProxy.java │ │ │ ├── ContentHandlerResource.java │ │ │ ├── ForkClient.java │ │ │ ├── ForkObjectInputStream.java │ │ │ ├── ForkParser.java │ │ │ ├── ForkProxy.java │ │ │ ├── ForkResource.java │ │ │ ├── ForkServer.java │ │ │ ├── InputStreamProxy.java │ │ │ ├── InputStreamResource.java │ │ │ ├── MemoryURLConnection.java │ │ │ ├── MemoryURLStreamHandler.java │ │ │ ├── MemoryURLStreamHandlerFactory.java │ │ │ ├── MemoryURLStreamRecord.java │ │ │ ├── MetadataContentHandler.java │ │ │ ├── ParserFactoryFactory.java │ │ │ ├── RecursiveMetadataContentHandlerProxy.java │ │ │ ├── RecursiveMetadataContentHandlerResource.java │ │ │ ├── TimeoutLimits.java │ │ │ └── package-info.java │ │ │ ├── io │ │ │ ├── BoundedInputStream.java │ │ │ ├── CloseShieldInputStream.java │ │ │ ├── ClosedInputStream.java │ │ │ ├── CountingInputStream.java │ │ │ ├── EndianUtils.java │ │ │ ├── FilenameUtils.java │ │ │ ├── IOExceptionWithCause.java │ │ │ ├── IOUtils.java │ │ │ ├── LookaheadInputStream.java │ │ │ ├── MappedBufferCleaner.java │ │ │ ├── NullInputStream.java │ │ │ ├── NullOutputStream.java │ │ │ ├── ProxyInputStream.java │ │ │ ├── TaggedIOException.java │ │ │ ├── TaggedInputStream.java │ │ │ ├── TailStream.java │ │ │ ├── TemporaryResources.java │ │ │ ├── TikaInputStream.java │ │ │ └── package-info.java │ │ │ ├── language │ │ │ ├── LanguageIdentifier.java │ │ │ ├── LanguageProfile.java │ │ │ ├── LanguageProfilerBuilder.java │ │ │ ├── ProfilingHandler.java │ │ │ ├── ProfilingWriter.java │ │ │ ├── detect │ │ │ │ ├── LanguageConfidence.java │ │ │ │ ├── LanguageDetector.java │ │ │ │ ├── LanguageHandler.java │ │ │ │ ├── LanguageNames.java │ │ │ │ ├── LanguageResult.java │ │ │ │ └── LanguageWriter.java │ │ │ └── translate │ │ │ │ ├── DefaultTranslator.java │ │ │ │ ├── EmptyTranslator.java │ │ │ │ └── Translator.java │ │ │ ├── metadata │ │ │ ├── AccessPermissions.java │ │ │ ├── ClimateForcast.java │ │ │ ├── CreativeCommons.java │ │ │ ├── Database.java │ │ │ ├── DublinCore.java │ │ │ ├── Font.java │ │ │ ├── Geographic.java │ │ │ ├── HTML.java │ │ │ ├── HttpHeaders.java │ │ │ ├── IPTC.java │ │ │ ├── MSOffice.java │ │ │ ├── Message.java │ │ │ ├── Metadata.java │ │ │ ├── Office.java │ │ │ ├── OfficeOpenXMLCore.java │ │ │ ├── OfficeOpenXMLExtended.java │ │ │ ├── PDF.java │ │ │ ├── PagedText.java │ │ │ ├── Photoshop.java │ │ │ ├── Property.java │ │ │ ├── PropertyTypeException.java │ │ │ ├── QuattroPro.java │ │ │ ├── RTFMetadata.java │ │ │ ├── TIFF.java │ │ │ ├── TikaCoreProperties.java │ │ │ ├── TikaMetadataKeys.java │ │ │ ├── TikaMimeKeys.java │ │ │ ├── WordPerfect.java │ │ │ ├── XMP.java │ │ │ ├── XMPDM.java │ │ │ ├── XMPIdq.java │ │ │ ├── XMPMM.java │ │ │ ├── XMPRights.java │ │ │ └── package-info.java │ │ │ ├── mime │ │ │ ├── AndClause.java │ │ │ ├── Clause.java │ │ │ ├── HexCoDec.java │ │ │ ├── Magic.java │ │ │ ├── MagicMatch.java │ │ │ ├── MediaType.java │ │ │ ├── MediaTypeRegistry.java │ │ │ ├── MimeType.java │ │ │ ├── MimeTypeException.java │ │ │ ├── MimeTypes.java │ │ │ ├── MimeTypesFactory.java │ │ │ ├── MimeTypesReader.java │ │ │ ├── MimeTypesReaderMetKeys.java │ │ │ ├── OrClause.java │ │ │ ├── Patterns.java │ │ │ ├── ProbabilisticMimeDetectionSelector.java │ │ │ └── package-info.java │ │ │ ├── package-info.java │ │ │ ├── parser │ │ │ ├── AbstractEncodingDetectorParser.java │ │ │ ├── AbstractParser.java │ │ │ ├── AutoDetectParser.java │ │ │ ├── AutoDetectParserFactory.java │ │ │ ├── CompositeParser.java │ │ │ ├── CryptoParser.java │ │ │ ├── DefaultParser.java │ │ │ ├── DelegatingParser.java │ │ │ ├── DigestingParser.java │ │ │ ├── EmptyParser.java │ │ │ ├── ErrorParser.java │ │ │ ├── NetworkParser.java │ │ │ ├── ParseContext.java │ │ │ ├── Parser.java │ │ │ ├── ParserDecorator.java │ │ │ ├── ParserFactory.java │ │ │ ├── ParserPostProcessor.java │ │ │ ├── ParsingReader.java │ │ │ ├── PasswordProvider.java │ │ │ ├── RecursiveParserWrapper.java │ │ │ ├── digest │ │ │ │ ├── CompositeDigester.java │ │ │ │ └── InputStreamDigester.java │ │ │ ├── external │ │ │ │ ├── CompositeExternalParser.java │ │ │ │ ├── ExternalParser.java │ │ │ │ ├── ExternalParsersConfigReader.java │ │ │ │ ├── ExternalParsersConfigReaderMetKeys.java │ │ │ │ ├── ExternalParsersFactory.java │ │ │ │ └── package-info.java │ │ │ └── package-info.java │ │ │ ├── sax │ │ │ ├── AbstractRecursiveParserWrapperHandler.java │ │ │ ├── BasicContentHandlerFactory.java │ │ │ ├── BodyContentHandler.java │ │ │ ├── CleanPhoneText.java │ │ │ ├── ContentHandlerDecorator.java │ │ │ ├── ContentHandlerFactory.java │ │ │ ├── DIFContentHandler.java │ │ │ ├── ElementMappingContentHandler.java │ │ │ ├── EmbeddedContentHandler.java │ │ │ ├── EndDocumentShieldingContentHandler.java │ │ │ ├── ExpandedTitleContentHandler.java │ │ │ ├── Link.java │ │ │ ├── LinkBuilder.java │ │ │ ├── LinkContentHandler.java │ │ │ ├── OfflineContentHandler.java │ │ │ ├── PhoneExtractingContentHandler.java │ │ │ ├── RecursiveParserWrapperHandler.java │ │ │ ├── RichTextContentHandler.java │ │ │ ├── SafeContentHandler.java │ │ │ ├── SecureContentHandler.java │ │ │ ├── StandardOrganizations.java │ │ │ ├── StandardReference.java │ │ │ ├── StandardsExtractingContentHandler.java │ │ │ ├── StandardsText.java │ │ │ ├── TaggedContentHandler.java │ │ │ ├── TaggedSAXException.java │ │ │ ├── TeeContentHandler.java │ │ │ ├── TextContentHandler.java │ │ │ ├── ToHTMLContentHandler.java │ │ │ ├── ToTextContentHandler.java │ │ │ ├── ToXMLContentHandler.java │ │ │ ├── WriteOutContentHandler.java │ │ │ ├── XHTMLContentHandler.java │ │ │ ├── XMPContentHandler.java │ │ │ ├── package-info.java │ │ │ └── xpath │ │ │ │ ├── AttributeMatcher.java │ │ │ │ ├── ChildMatcher.java │ │ │ │ ├── CompositeMatcher.java │ │ │ │ ├── ElementMatcher.java │ │ │ │ ├── Matcher.java │ │ │ │ ├── MatchingContentHandler.java │ │ │ │ ├── NamedAttributeMatcher.java │ │ │ │ ├── NamedElementMatcher.java │ │ │ │ ├── NodeMatcher.java │ │ │ │ ├── SubtreeMatcher.java │ │ │ │ ├── TextMatcher.java │ │ │ │ ├── XPathParser.java │ │ │ │ └── package-info.java │ │ │ └── utils │ │ │ ├── AnnotationUtils.java │ │ │ ├── CharsetUtils.java │ │ │ ├── ConcurrentUtils.java │ │ │ ├── DateUtils.java │ │ │ ├── ExceptionUtils.java │ │ │ ├── ParserUtils.java │ │ │ ├── ProcessUtils.java │ │ │ ├── RegexUtils.java │ │ │ ├── RereadableInputStream.java │ │ │ ├── ServiceLoaderUtils.java │ │ │ ├── SystemUtils.java │ │ │ ├── XMLReaderUtils.java │ │ │ └── package-info.java │ └── resources │ │ └── org │ │ └── apache │ │ └── tika │ │ ├── detect │ │ └── tika-example.nnmodel │ │ ├── language │ │ ├── be.ngp │ │ ├── ca.ngp │ │ ├── da.ngp │ │ ├── de.ngp │ │ ├── el.ngp │ │ ├── en.ngp │ │ ├── eo.ngp │ │ ├── es.ngp │ │ ├── et.ngp │ │ ├── fa.ngp │ │ ├── fi.ngp │ │ ├── fr.ngp │ │ ├── gl.ngp │ │ ├── hu.ngp │ │ ├── is.ngp │ │ ├── it.ngp │ │ ├── lt.ngp │ │ ├── nl.ngp │ │ ├── no.ngp │ │ ├── pl.ngp │ │ ├── pt.ngp │ │ ├── ro.ngp │ │ ├── ru.ngp │ │ ├── sk.ngp │ │ ├── sl.ngp │ │ ├── sv.ngp │ │ ├── th.ngp │ │ ├── tika.language.properties │ │ └── uk.ngp │ │ ├── mime │ │ └── tika-mimetypes.xml │ │ └── parser │ │ └── external │ │ └── tika-external-parsers.xml │ └── test │ ├── java │ └── org │ │ └── apache │ │ └── tika │ │ ├── MultiThreadedTikaTest.java │ │ ├── ResourceLoggingClassLoader.java │ │ ├── TestRereadableInputStream.java │ │ ├── TikaDetectionTest.java │ │ ├── TikaIT.java │ │ ├── TikaTest.java │ │ ├── TypeDetectionBenchmark.java │ │ ├── config │ │ ├── AbstractTikaConfigTest.java │ │ ├── DummyExecutor.java │ │ ├── DummyParser.java │ │ ├── ParamTest.java │ │ ├── TikaConfigSerializerTest.java │ │ └── TikaConfigTest.java │ │ ├── detect │ │ ├── MagicDetectorTest.java │ │ ├── MimeDetectionWithNNTest.java │ │ ├── NameDetectorTest.java │ │ ├── TextDetectorTest.java │ │ ├── TypeDetectorTest.java │ │ └── ZeroSizeFileDetectorTest.java │ │ ├── fork │ │ ├── ForkParserTest.java │ │ ├── ForkParserTikaBinTest.java │ │ ├── ForkTestParser.java │ │ ├── UpperCasingContentHandler.java │ │ └── unusedpackage │ │ │ └── ClassInUnusedPackage.java │ │ ├── io │ │ ├── EndianUtilsTest.java │ │ ├── FilenameUtilsTest.java │ │ ├── LookaheadInputStreamTest.java │ │ ├── TaggedInputStreamTest.java │ │ ├── TailStreamTest.java │ │ ├── TemporaryResourcesTest.java │ │ └── TikaInputStreamTest.java │ │ ├── language │ │ ├── LanguageIdentifierTest.java │ │ ├── LanguageProfileTest.java │ │ ├── LanguageProfilerBuilderTest.java │ │ ├── ProfilingWriterTest.java │ │ └── detect │ │ │ └── LanguageNamesTest.java │ │ ├── metadata │ │ └── TestMetadata.java │ │ ├── mime │ │ ├── CustomReaderTest.java │ │ ├── MediaTypeTest.java │ │ ├── MimeDetectionTest.java │ │ ├── MimeTypesReaderTest.java │ │ ├── PatternsTest.java │ │ ├── ProbabilisticMimeDetectionTest.java │ │ └── ProbabilisticMimeDetectionTestWithTika.java │ │ ├── parser │ │ ├── CompositeParserTest.java │ │ ├── DummyInitializableParser.java │ │ ├── DummyParameterizedParser.java │ │ ├── DummyParser.java │ │ ├── InitializableParserTest.java │ │ ├── ParameterizedParserTest.java │ │ ├── ParserDecoratorTest.java │ │ └── mock │ │ │ ├── MockParser.java │ │ │ ├── MockParserFactory.java │ │ │ └── VowelParser.java │ │ ├── sax │ │ ├── BasicContentHandlerFactoryTest.java │ │ ├── BodyContentHandlerTest.java │ │ ├── LinkContentHandlerTest.java │ │ ├── OfflineContentHandlerTest.java │ │ ├── RichTextContentHandlerTest.java │ │ ├── SafeContentHandlerTest.java │ │ ├── SecureContentHandlerTest.java │ │ ├── SerializerTest.java │ │ ├── XHTMLContentHandlerTest.java │ │ └── xpath │ │ │ └── XPathParserTest.java │ │ └── utils │ │ ├── AnnotationUtilsTest.java │ │ ├── CharsetUtilsTest.java │ │ ├── ConcurrentUtilsTest.java │ │ └── RegexUtilsTest.java │ └── resources │ ├── META-INF │ └── services │ │ └── org.apache.tika.parser.Parser │ ├── log4j.properties │ ├── org │ └── apache │ │ └── tika │ │ ├── config │ │ ├── TIKA-1445-default-except.xml │ │ ├── TIKA-1508-configurable.xml │ │ ├── TIKA-1642-CTakes.xml │ │ ├── TIKA-1653-norepeat.xml │ │ ├── TIKA-1700-dynamic.xml │ │ ├── TIKA-1700-unknown-parser.xml │ │ ├── TIKA-1762-executors.xml │ │ ├── TIKA-1986-bad-parameters.xml │ │ ├── TIKA-1986-bad-types.xml │ │ ├── TIKA-1986-bad-values.xml │ │ ├── TIKA-1986-initializable.xml │ │ ├── TIKA-1986-parameterized-decorated.xml │ │ ├── TIKA-1986-parameterized.xml │ │ ├── TIKA-1986-some-parameters.xml │ │ ├── TIKA-2389-illegal.xml │ │ ├── TIKA-2389-throw-default-overridden.xml │ │ ├── TIKA-2389-throw-default.xml │ │ ├── TIKA-2389-throw-per-parser.xml │ │ ├── TIKA-2389-warn-per-parser.xml │ │ ├── TIKA-2653-vowel-parser-ae.xml │ │ ├── TIKA-2653-vowel-parser-iou.xml │ │ ├── TIKA-2732-xmlreaderutils-exc.xml │ │ ├── TIKA-2732-xmlreaderutils.xml │ │ ├── TIKA-866-composite.xml │ │ ├── TIKA-866-invalid.xml │ │ └── TIKA-866-valid.xml │ │ ├── detect │ │ └── tika-example.nnmodel │ │ ├── io │ │ └── test.txt │ │ ├── language │ │ ├── da.test │ │ ├── de.test │ │ ├── el.test │ │ ├── en.test │ │ ├── es.test │ │ ├── et.test │ │ ├── fi.test │ │ ├── fr.test │ │ ├── it.test │ │ ├── langbuilder │ │ │ └── welsh_corpus.txt │ │ ├── lt.test │ │ ├── nl.test │ │ ├── pt.test │ │ └── sv.test │ │ └── mime │ │ ├── GLDAS_CLM10SUBP_3H.A19790202.0000.001.grb │ │ ├── brwNIMS_2014.dif │ │ ├── circles-with-prefix.svg │ │ ├── circles.svg │ │ ├── custom-mimetypes.xml │ │ ├── custom-mimetypes2.xml │ │ ├── datamatrix.png │ │ ├── external-mimetypes.xml │ │ ├── gdas1.forecmwf.2014062612.grib2 │ │ ├── htmlfragment │ │ ├── plotutils-bin-cgm-v3.cgm │ │ ├── stylesheet.xsl │ │ ├── test-difficult-rdf1.xml │ │ ├── test-difficult-rdf2.xml │ │ ├── test-iso-8859-1.xml │ │ ├── test-long-comment.xml │ │ ├── test-malformed-header.html.bin │ │ ├── test-tika-327.html │ │ ├── test-utf16be.xml │ │ ├── test-utf16le.xml │ │ ├── test-utf8-bom.xml │ │ ├── test-utf8.xml │ │ ├── test.html │ │ ├── test.xls │ │ └── testlargerbuffer.html │ └── test-documents │ ├── ang20150420t182050_corr_v1e_img.hdr │ ├── basic_embedded.xml │ ├── embedded_then_npe.xml │ ├── embedded_with_npe.xml │ └── example.xml ├── tika-deployment ├── tika-snap-app │ └── snapcraft.yaml └── tika-snap-server │ └── snapcraft.yaml ├── tika-dl ├── pom.xml └── src │ ├── main │ └── java │ │ └── org │ │ └── apache │ │ └── tika │ │ └── dl │ │ └── imagerec │ │ ├── DL4JInceptionV3Net.java │ │ └── DL4JVGG16Net.java │ └── test │ ├── java │ └── org │ │ └── apache │ │ └── tika │ │ └── dl │ │ └── imagerec │ │ ├── DL4JInceptionV3NetTest.java │ │ └── DL4JVGG16NetTest.java │ └── resources │ └── org │ └── apache │ └── tika │ └── dl │ └── imagerec │ ├── cat.jpg │ ├── dl4j-inception3-config.xml │ ├── dl4j-vgg16-config.xml │ └── lion.jpg ├── tika-dotnet ├── pom.xml └── src │ └── main │ └── java │ └── Tika │ └── Tika.java ├── tika-eval ├── .gitignore ├── pom.xml └── src │ ├── main │ ├── java │ │ └── org │ │ │ └── apache │ │ │ └── tika │ │ │ └── eval │ │ │ ├── AbstractProfiler.java │ │ │ ├── EvalFilePaths.java │ │ │ ├── ExtractComparer.java │ │ │ ├── ExtractProfiler.java │ │ │ ├── TikaEvalCLI.java │ │ │ ├── XMLErrorLogUpdater.java │ │ │ ├── batch │ │ │ ├── DBConsumersManager.java │ │ │ ├── EvalConsumerBuilder.java │ │ │ ├── EvalConsumersBuilder.java │ │ │ ├── ExtractComparerBuilder.java │ │ │ └── ExtractProfilerBuilder.java │ │ │ ├── db │ │ │ ├── AbstractDBBuffer.java │ │ │ ├── ColInfo.java │ │ │ ├── Cols.java │ │ │ ├── DBBuffer.java │ │ │ ├── H2Util.java │ │ │ ├── JDBCUtil.java │ │ │ ├── MimeBuffer.java │ │ │ └── TableInfo.java │ │ │ ├── io │ │ │ ├── DBWriter.java │ │ │ ├── ExtractReader.java │ │ │ ├── ExtractReaderException.java │ │ │ ├── IDBWriter.java │ │ │ ├── XMLLogMsgHandler.java │ │ │ └── XMLLogReader.java │ │ │ ├── langid │ │ │ ├── Language.java │ │ │ ├── LanguageIDWrapper.java │ │ │ └── ProbingLanguageDetector.java │ │ │ ├── reports │ │ │ ├── Report.java │ │ │ ├── ResultsReporter.java │ │ │ ├── XLSXHREFFormatter.java │ │ │ ├── XLSXNumFormatter.java │ │ │ └── XSLXCellFormatter.java │ │ │ ├── textstats │ │ │ ├── BasicTokenCountStatsCalculator.java │ │ │ ├── CommonTokens.java │ │ │ ├── CommonTokensBhattacharyya.java │ │ │ ├── CommonTokensCosine.java │ │ │ ├── CommonTokensHellinger.java │ │ │ ├── CommonTokensKLDNormed.java │ │ │ ├── CommonTokensKLDivergence.java │ │ │ ├── CompositeTextStatsCalculator.java │ │ │ ├── ContentLengthCalculator.java │ │ │ ├── LanguageAwareTokenCountStats.java │ │ │ ├── StringStatsCalculator.java │ │ │ ├── TextStatsCalculator.java │ │ │ ├── TokenCountPriorityQueue.java │ │ │ ├── TokenCountStatsCalculator.java │ │ │ ├── TokenEntropy.java │ │ │ ├── TokenLengths.java │ │ │ ├── TopNTokens.java │ │ │ └── UnicodeBlockCounter.java │ │ │ ├── tokens │ │ │ ├── AlphaIdeographFilterFactory.java │ │ │ ├── AnalyzerDeserializer.java │ │ │ ├── AnalyzerManager.java │ │ │ ├── CJKBigramAwareLengthFilterFactory.java │ │ │ ├── CommonTokenCountManager.java │ │ │ ├── CommonTokenResult.java │ │ │ ├── ContrastStatistics.java │ │ │ ├── LangModel.java │ │ │ ├── TokenContraster.java │ │ │ ├── TokenCountPriorityQueue.java │ │ │ ├── TokenCounter.java │ │ │ ├── TokenCounts.java │ │ │ ├── TokenIntPair.java │ │ │ ├── TokenStatistics.java │ │ │ └── URLEmailNormalizingFilterFactory.java │ │ │ ├── tools │ │ │ ├── BatchTopCommonTokenCounter.java │ │ │ ├── CommonTokenOverlapCounter.java │ │ │ ├── LeipzigHelper.java │ │ │ ├── LeipzigSampler.java │ │ │ ├── SlowCompositeReaderWrapper.java │ │ │ ├── TopCommonTokenCounter.java │ │ │ └── TrainTestSplit.java │ │ │ └── util │ │ │ ├── ContentTagParser.java │ │ │ ├── ContentTags.java │ │ │ └── EvalExceptionUtils.java │ └── resources │ │ ├── META-INF │ │ └── services │ │ │ └── org.apache.lucene.analysis.util.TokenFilterFactory │ │ ├── common_tokens │ │ ├── afr │ │ ├── amh │ │ ├── ara │ │ ├── asm │ │ ├── ast │ │ ├── aze │ │ ├── azj │ │ ├── bak │ │ ├── ban │ │ ├── bel │ │ ├── ben │ │ ├── bos │ │ ├── bre │ │ ├── bul │ │ ├── cat │ │ ├── ceb │ │ ├── ces │ │ ├── che │ │ ├── ckb │ │ ├── cmn │ │ ├── cym │ │ ├── dan │ │ ├── deu │ │ ├── div │ │ ├── ekk │ │ ├── ell │ │ ├── eng │ │ ├── epo │ │ ├── est │ │ ├── eus │ │ ├── fao │ │ ├── fas │ │ ├── fin │ │ ├── fra │ │ ├── fry │ │ ├── gle │ │ ├── glg │ │ ├── gsw │ │ ├── guj │ │ ├── hat │ │ ├── heb │ │ ├── hin │ │ ├── hrv │ │ ├── hun │ │ ├── hye │ │ ├── ind │ │ ├── isl │ │ ├── ita │ │ ├── jav │ │ ├── jpn │ │ ├── kan │ │ ├── kat │ │ ├── kaz │ │ ├── kin │ │ ├── kir │ │ ├── kor │ │ ├── kur │ │ ├── lat │ │ ├── lav │ │ ├── lim │ │ ├── lit │ │ ├── ltz │ │ ├── lug │ │ ├── lvs │ │ ├── mal │ │ ├── mar │ │ ├── mhr │ │ ├── min │ │ ├── mkd │ │ ├── mlg │ │ ├── mlt │ │ ├── mon │ │ ├── mri │ │ ├── msa │ │ ├── nan │ │ ├── nds │ │ ├── nep │ │ ├── nld │ │ ├── nno │ │ ├── nob │ │ ├── oci │ │ ├── ori │ │ ├── pan │ │ ├── pes │ │ ├── plt │ │ ├── pnb │ │ ├── pol │ │ ├── por │ │ ├── pus │ │ ├── ron │ │ ├── rus │ │ ├── san │ │ ├── sin │ │ ├── slk │ │ ├── slv │ │ ├── snd │ │ ├── som │ │ ├── spa │ │ ├── sqi │ │ ├── srp │ │ ├── sun │ │ ├── swa │ │ ├── swe │ │ ├── tam │ │ ├── tat │ │ ├── tel │ │ ├── tgk │ │ ├── tgl │ │ ├── tha │ │ ├── tuk │ │ ├── tur │ │ ├── uig │ │ ├── ukr │ │ ├── urd │ │ ├── uzb │ │ ├── vie │ │ ├── vol │ │ ├── war │ │ ├── xho │ │ ├── yid │ │ └── zul │ │ ├── comparison-reports-pg.xml │ │ ├── comparison-reports.xml │ │ ├── db.properties │ │ ├── log4j.properties │ │ ├── lucene-analyzers.json │ │ ├── lucene-char-mapping.txt │ │ ├── opennlp │ │ └── model_20190626.bin │ │ ├── profile-reports.xml │ │ ├── tika-eval-comparison-config.xml │ │ └── tika-eval-profiler-config.xml │ └── test │ ├── java │ └── org │ │ └── apache │ │ └── tika │ │ ├── MockDBWriter.java │ │ ├── eval │ │ ├── AnalyzerManagerTest.java │ │ ├── ComparerBatchTest.java │ │ ├── ProfilerBatchTest.java │ │ ├── SimpleComparerTest.java │ │ ├── TikaEvalCLITest.java │ │ ├── db │ │ │ └── AbstractBufferTest.java │ │ ├── io │ │ │ ├── ExtractReaderTest.java │ │ │ └── FatalExceptionReaderTest.java │ │ ├── langid │ │ │ └── LangIdTest.java │ │ ├── reports │ │ │ └── ResultsReporterTest.java │ │ ├── tokens │ │ │ ├── LuceneTokenCounter.java │ │ │ └── TokenCounterTest.java │ │ └── util │ │ │ ├── LanguageIdTest.java │ │ │ └── MimeUtilTest.java │ │ └── tools │ │ └── TopCommonTokenCounterTest.java │ └── resources │ ├── common_tokens │ ├── en │ ├── es │ ├── zh-cn │ └── zh-tw │ ├── single-file-profiler-crawl-extract-config.xml │ ├── single-file-profiler-crawl-input-config.xml │ └── test-dirs │ ├── batch-logs │ └── batch-process-fatal.xml │ ├── extractsA │ ├── file1.pdf.json │ ├── file10_permahang.txt.json │ ├── file11_oom.txt.json │ ├── file12_es.txt.json │ ├── file13_attachANotB.doc.json │ ├── file14_diffAttachOrder.json │ ├── file15_tags.json │ ├── file16_badTags.json │ ├── file17_tagsOutOfOrder.json │ ├── file2_attachANotB.doc.json │ ├── file3_attachBNotA.doc.json │ ├── file4_emptyB.pdf.json │ ├── file5_emptyA.pdf.json │ ├── file6_accessEx.pdf.json │ ├── file7_badJson.pdf.json │ └── file8_IOEx.pdf.json │ ├── extractsB │ ├── file1.pdf.json │ ├── file11_oom.txt.json │ ├── file12_es.txt.json │ ├── file13_attachANotB.doc.txt │ ├── file14_diffAttachOrder.json │ ├── file15_tags.html │ ├── file16_badTags.html │ ├── file2_attachANotB.doc.json │ ├── file3_attachBNotA.doc.json │ ├── file4_emptyB.pdf.json │ ├── file5_emptyA.pdf.json │ ├── file6_accessEx.pdf.json │ ├── file7_badJson.pdf.json │ └── file8_IOEx.pdf.json │ └── raw_input │ ├── file1.pdf │ ├── file11_oom.txt │ ├── file2_attachANotB.doc │ ├── file3_attachBNotA.doc │ ├── file4_emptyB.pdf │ ├── file5_emptyA.pdf │ ├── file6_accessEx.pdf │ ├── file7_badJson.pdf │ ├── file8_IOEx.pdf │ └── file9_noextract.txt ├── tika-example ├── pom.xml └── src │ ├── main │ ├── java │ │ └── org │ │ │ └── apache │ │ │ └── tika │ │ │ └── example │ │ │ ├── AdvancedTypeDetector.java │ │ │ ├── ContentHandlerExample.java │ │ │ ├── CustomMimeInfo.java │ │ │ ├── DescribeMetadata.java │ │ │ ├── DirListParser.java │ │ │ ├── DisplayMetInstance.java │ │ │ ├── DumpTikaConfigExample.java │ │ │ ├── EncryptedPrescriptionDetector.java │ │ │ ├── EncryptedPrescriptionParser.java │ │ │ ├── ExtractEmbeddedFiles.java │ │ │ ├── GrabPhoneNumbersExample.java │ │ │ ├── ImportContextImpl.java │ │ │ ├── InterruptableParsingExample.java │ │ │ ├── Language.java │ │ │ ├── LanguageDetectingParser.java │ │ │ ├── LanguageDetectorExample.java │ │ │ ├── LuceneIndexer.java │ │ │ ├── LuceneIndexerExtended.java │ │ │ ├── MediaTypeExample.java │ │ │ ├── MetadataAwareLuceneIndexer.java │ │ │ ├── MyFirstTika.java │ │ │ ├── ParsingExample.java │ │ │ ├── Pharmacy.java │ │ │ ├── PrescriptionParser.java │ │ │ ├── RecentFiles.java │ │ │ ├── RollbackSoftware.java │ │ │ ├── SimpleTextExtractor.java │ │ │ ├── SimpleTypeDetector.java │ │ │ ├── SpringExample.java │ │ │ ├── StandardsExtractionExample.java │ │ │ ├── TIAParsingExample.java │ │ │ ├── TextStatsFromTikaEval.java │ │ │ ├── TranslatorExample.java │ │ │ ├── TrecDocumentGenerator.java │ │ │ └── ZipListFiles.java │ └── resources │ │ └── org │ │ └── apache │ │ └── tika │ │ └── example │ │ ├── spring.xml │ │ ├── test.doc │ │ ├── test2.doc │ │ └── test_recursive_embedded.docx │ └── test │ └── java │ └── org │ └── apache │ └── tika │ └── example │ ├── AdvancedTypeDetectorTest.java │ ├── ContentHandlerExampleTest.java │ ├── DumpTikaConfigExampleTest.java │ ├── ExtractEmbeddedFilesTest.java │ ├── LanguageDetectorExampleTest.java │ ├── SimpleTextExtractorTest.java │ ├── SimpleTypeDetectorTest.java │ ├── TestParsingExample.java │ ├── TextStatsFromTikaEvalTest.java │ └── TranslatorExampleTest.java ├── tika-java7 ├── pom.xml └── src │ ├── main │ ├── java │ │ └── org │ │ │ └── apache │ │ │ └── tika │ │ │ └── filetypedetector │ │ │ ├── TikaFileTypeDetector.java │ │ │ └── package-info.java │ └── resources │ │ └── META-INF │ │ └── services │ │ └── java.nio.file.spi.FileTypeDetector │ └── test │ ├── java │ └── org │ │ └── apache │ │ └── tika │ │ └── filetypedetector │ │ └── TikaFileTypeDetectorTest.java │ └── resources │ └── test-documents │ └── test.html ├── tika-langdetect ├── pom.xml └── src │ ├── main │ ├── java │ │ └── org │ │ │ └── apache │ │ │ └── tika │ │ │ └── langdetect │ │ │ ├── Lingo24LangDetector.java │ │ │ ├── OptimaizeLangDetector.java │ │ │ └── TextLangDetector.java │ └── resources │ │ ├── META-INF │ │ └── services │ │ │ └── org.apache.tika.language.detect.LanguageDetector │ │ └── org │ │ └── apache │ │ └── tika │ │ └── langdetect │ │ └── langdetect.lingo24.properties │ └── test │ ├── java │ └── org │ │ └── apache │ │ └── tika │ │ └── langdetect │ │ ├── LanguageDetectorTest.java │ │ ├── Lingo24LangDetectorTest.java │ │ ├── OptimaizeLangDetectorTest.java │ │ └── TextLangDetectorTest.java │ └── resources │ ├── log4j.properties │ └── org │ └── apache │ └── tika │ └── langdetect │ ├── language-codes.txt │ ├── language-tests │ ├── da.test │ ├── de.test │ ├── el.test │ ├── en.test │ ├── es.test │ ├── et.test │ ├── fi.test │ ├── fr.test │ ├── it.test │ ├── ja.test │ ├── lt.test │ ├── nl.test │ ├── pt.test │ ├── sv.test │ ├── th.test │ └── zh.test │ ├── text-test.tsv │ ├── udhr-known.txt │ └── udhr-unknown.txt ├── tika-nlp ├── pom.xml └── src │ ├── main │ └── java │ │ └── org │ │ └── apache │ │ └── tika │ │ └── parser │ │ └── recognition │ │ ├── AgeRecogniser.java │ │ └── AgeRecogniserConfig.java │ └── test │ ├── java │ └── org │ │ └── apache │ │ └── tika │ │ └── parser │ │ └── recognition │ │ └── AgeRecogniserTest.java │ └── resources │ └── org │ └── apache │ └── tika │ └── parser │ └── recognition │ └── tika-config-age.xml ├── tika-parent └── pom.xml ├── tika-parsers ├── .gitignore ├── pom.xml └── src │ ├── main │ ├── appended-resources │ │ └── META-INF │ │ │ └── LICENSE │ ├── java │ │ └── org │ │ │ └── apache │ │ │ └── tika │ │ │ └── parser │ │ │ ├── apple │ │ │ └── AppleSingleFileParser.java │ │ │ ├── asm │ │ │ ├── ClassParser.java │ │ │ └── XHTMLClassVisitor.java │ │ │ ├── audio │ │ │ ├── AudioParser.java │ │ │ └── MidiParser.java │ │ │ ├── captioning │ │ │ ├── CaptionObject.java │ │ │ └── tf │ │ │ │ └── TensorflowRESTCaptioner.java │ │ │ ├── chm │ │ │ ├── ChmParser.java │ │ │ ├── accessor │ │ │ │ ├── ChmAccessor.java │ │ │ │ ├── ChmDirectoryListingSet.java │ │ │ │ ├── ChmItsfHeader.java │ │ │ │ ├── ChmItspHeader.java │ │ │ │ ├── ChmLzxcControlData.java │ │ │ │ ├── ChmLzxcResetTable.java │ │ │ │ ├── ChmPmgiHeader.java │ │ │ │ ├── ChmPmglHeader.java │ │ │ │ └── DirectoryListingEntry.java │ │ │ ├── assertion │ │ │ │ └── ChmAssert.java │ │ │ ├── core │ │ │ │ ├── ChmCommons.java │ │ │ │ ├── ChmConstants.java │ │ │ │ ├── ChmExtractor.java │ │ │ │ └── ChmWrapper.java │ │ │ ├── exception │ │ │ │ └── ChmParsingException.java │ │ │ └── lzx │ │ │ │ ├── ChmBlockInfo.java │ │ │ │ ├── ChmLzxBlock.java │ │ │ │ ├── ChmLzxState.java │ │ │ │ └── ChmSection.java │ │ │ ├── code │ │ │ └── SourceCodeParser.java │ │ │ ├── crypto │ │ │ ├── Pkcs7Parser.java │ │ │ └── TSDParser.java │ │ │ ├── csv │ │ │ ├── CSVParams.java │ │ │ ├── CSVResult.java │ │ │ ├── CSVSniffer.java │ │ │ └── TextAndCSVParser.java │ │ │ ├── ctakes │ │ │ ├── CTAKESAnnotationProperty.java │ │ │ ├── CTAKESConfig.java │ │ │ ├── CTAKESContentHandler.java │ │ │ ├── CTAKESParser.java │ │ │ ├── CTAKESSerializer.java │ │ │ └── CTAKESUtils.java │ │ │ ├── dbf │ │ │ ├── DBFCell.java │ │ │ ├── DBFColumnHeader.java │ │ │ ├── DBFFileHeader.java │ │ │ ├── DBFParser.java │ │ │ ├── DBFReader.java │ │ │ └── DBFRow.java │ │ │ ├── dif │ │ │ ├── DIFContentHandler.java │ │ │ └── DIFParser.java │ │ │ ├── dwg │ │ │ └── DWGParser.java │ │ │ ├── envi │ │ │ └── EnviHeaderParser.java │ │ │ ├── epub │ │ │ ├── EpubContentParser.java │ │ │ └── EpubParser.java │ │ │ ├── executable │ │ │ ├── ExecutableParser.java │ │ │ └── MachineMetadata.java │ │ │ ├── feed │ │ │ └── FeedParser.java │ │ │ ├── font │ │ │ ├── AdobeFontMetricParser.java │ │ │ └── TrueTypeParser.java │ │ │ ├── gdal │ │ │ └── GDALParser.java │ │ │ ├── geo │ │ │ └── topic │ │ │ │ ├── GeoParser.java │ │ │ │ ├── GeoParserConfig.java │ │ │ │ ├── GeoTag.java │ │ │ │ ├── NameEntityExtractor.java │ │ │ │ └── gazetteer │ │ │ │ ├── GeoGazetteerClient.java │ │ │ │ └── Location.java │ │ │ ├── geoinfo │ │ │ └── GeographicInformationParser.java │ │ │ ├── grib │ │ │ └── GribParser.java │ │ │ ├── hdf │ │ │ └── HDFParser.java │ │ │ ├── html │ │ │ ├── BoilerpipeContentHandler.java │ │ │ ├── DefaultHtmlMapper.java │ │ │ ├── HtmlEncodingDetector.java │ │ │ ├── HtmlHandler.java │ │ │ ├── HtmlMapper.java │ │ │ ├── HtmlParser.java │ │ │ ├── IdentityHtmlMapper.java │ │ │ ├── XHTMLDowngradeHandler.java │ │ │ └── charsetdetector │ │ │ │ ├── CharsetAliases.java │ │ │ │ ├── CharsetDetectionResult.java │ │ │ │ ├── MetaProcessor.java │ │ │ │ ├── PreScanner.java │ │ │ │ ├── StandardHtmlEncodingDetector.java │ │ │ │ └── charsets │ │ │ │ ├── ReplacementCharset.java │ │ │ │ └── XUserDefinedCharset.java │ │ │ ├── hwp │ │ │ ├── HwpStreamReader.java │ │ │ ├── HwpTextExtractorV5.java │ │ │ └── HwpV5Parser.java │ │ │ ├── image │ │ │ ├── BPGParser.java │ │ │ ├── ICNSParser.java │ │ │ ├── ICNSType.java │ │ │ ├── ImageMetadataExtractor.java │ │ │ ├── ImageParser.java │ │ │ ├── MetadataFields.java │ │ │ ├── PSDParser.java │ │ │ ├── TiffParser.java │ │ │ ├── WebPParser.java │ │ │ └── xmp │ │ │ │ ├── JempboxExtractor.java │ │ │ │ └── XMPPacketScanner.java │ │ │ ├── internal │ │ │ └── Activator.java │ │ │ ├── iptc │ │ │ └── IptcAnpaParser.java │ │ │ ├── isatab │ │ │ ├── ISATabUtils.java │ │ │ └── ISArchiveParser.java │ │ │ ├── iwork │ │ │ ├── AutoPageNumberUtils.java │ │ │ ├── IWorkPackageParser.java │ │ │ ├── KeynoteContentHandler.java │ │ │ ├── NumbersContentHandler.java │ │ │ ├── PagesContentHandler.java │ │ │ └── iwana │ │ │ │ ├── IWork13PackageParser.java │ │ │ │ └── IWork18PackageParser.java │ │ │ ├── jdbc │ │ │ ├── AbstractDBParser.java │ │ │ ├── JDBCTableReader.java │ │ │ ├── SQLite3DBParser.java │ │ │ ├── SQLite3Parser.java │ │ │ └── SQLite3TableReader.java │ │ │ ├── journal │ │ │ ├── GrobidRESTParser.java │ │ │ ├── JournalParser.java │ │ │ └── TEIDOMParser.java │ │ │ ├── jpeg │ │ │ └── JpegParser.java │ │ │ ├── mail │ │ │ ├── MailContentHandler.java │ │ │ ├── MailUtil.java │ │ │ └── RFC822Parser.java │ │ │ ├── mat │ │ │ └── MatParser.java │ │ │ ├── mbox │ │ │ ├── MboxParser.java │ │ │ └── OutlookPSTParser.java │ │ │ ├── microsoft │ │ │ ├── AbstractListManager.java │ │ │ ├── AbstractOfficeParser.java │ │ │ ├── AbstractPOIFSExtractor.java │ │ │ ├── Cell.java │ │ │ ├── CellDecorator.java │ │ │ ├── EMFParser.java │ │ │ ├── ExcelExtractor.java │ │ │ ├── FormattingUtils.java │ │ │ ├── HSLFExtractor.java │ │ │ ├── JackcessExtractor.java │ │ │ ├── JackcessParser.java │ │ │ ├── LinkedCell.java │ │ │ ├── ListManager.java │ │ │ ├── MSOwnerFileParser.java │ │ │ ├── NumberCell.java │ │ │ ├── OfficeParser.java │ │ │ ├── OfficeParserConfig.java │ │ │ ├── OldExcelParser.java │ │ │ ├── OutlookExtractor.java │ │ │ ├── POIFSContainerDetector.java │ │ │ ├── SummaryExtractor.java │ │ │ ├── TNEFParser.java │ │ │ ├── TextCell.java │ │ │ ├── TikaExcelDataFormatter.java │ │ │ ├── TikaExcelGeneralFormat.java │ │ │ ├── WMFParser.java │ │ │ ├── WordExtractor.java │ │ │ ├── onenote │ │ │ │ ├── CheckedFileNodePushBack.java │ │ │ │ ├── CompactID.java │ │ │ │ ├── Error.java │ │ │ │ ├── ExtendedGUID.java │ │ │ │ ├── FileChunkReference.java │ │ │ │ ├── FileDataStoreObject.java │ │ │ │ ├── FileDataStoreObjectReference.java │ │ │ │ ├── FileNode.java │ │ │ │ ├── FileNodeList.java │ │ │ │ ├── FileNodeListHeader.java │ │ │ │ ├── FileNodePtr.java │ │ │ │ ├── FileNodePtrBackPush.java │ │ │ │ ├── FileNodeUnion.java │ │ │ │ ├── FndStructureConstants.java │ │ │ │ ├── GUID.java │ │ │ │ ├── GlobalIdTableEntry2FNDX.java │ │ │ │ ├── GlobalIdTableEntry3FNDX.java │ │ │ │ ├── GlobalIdTableEntryFNDX.java │ │ │ │ ├── GlobalIdTableStartFNDX.java │ │ │ │ ├── IndentUtil.java │ │ │ │ ├── Int24.java │ │ │ │ ├── JCID.java │ │ │ │ ├── JCIDPropertySetTypeEnum.java │ │ │ │ ├── ObjectDeclarationWithRefCount.java │ │ │ │ ├── ObjectDeclarationWithRefCountBody.java │ │ │ │ ├── ObjectInfoDependencyOverrideData.java │ │ │ │ ├── ObjectInfoDependencyOverrides.java │ │ │ │ ├── ObjectRevisionWithRefCountFNDX.java │ │ │ │ ├── ObjectSpaceObjectPropSet.java │ │ │ │ ├── ObjectSpaceObjectStreamOfOIDsOSIDsOrContextIDs.java │ │ │ │ ├── ObjectStreamCounters.java │ │ │ │ ├── OneNoteDirectFileResource.java │ │ │ │ ├── OneNoteDocument.java │ │ │ │ ├── OneNoteHeader.java │ │ │ │ ├── OneNoteLegacyDumpStrings.java │ │ │ │ ├── OneNoteParser.java │ │ │ │ ├── OneNotePropertyEnum.java │ │ │ │ ├── OneNotePropertyId.java │ │ │ │ ├── OneNotePtr.java │ │ │ │ ├── OneNoteTreeWalker.java │ │ │ │ ├── OneNoteTreeWalkerOptions.java │ │ │ │ ├── PropertyIDType.java │ │ │ │ ├── PropertySet.java │ │ │ │ ├── PropertyValue.java │ │ │ │ ├── Revision.java │ │ │ │ ├── RevisionManifest.java │ │ │ │ ├── RevisionManifestListStart.java │ │ │ │ ├── RevisionRoleDeclaration.java │ │ │ │ ├── RootObjectReference.java │ │ │ │ └── RootObjectReferenceBase.java │ │ │ ├── ooxml │ │ │ │ ├── AbstractOOXMLExtractor.java │ │ │ │ ├── MetadataExtractor.java │ │ │ │ ├── OOXMLExtractor.java │ │ │ │ ├── OOXMLExtractorFactory.java │ │ │ │ ├── OOXMLParser.java │ │ │ │ ├── OOXMLTikaBodyPartHandler.java │ │ │ │ ├── OOXMLWordAndPowerPointTextHandler.java │ │ │ │ ├── POIXMLTextExtractorDecorator.java │ │ │ │ ├── ParagraphProperties.java │ │ │ │ ├── RunProperties.java │ │ │ │ ├── SXSLFPowerPointExtractorDecorator.java │ │ │ │ ├── SXWPFWordExtractorDecorator.java │ │ │ │ ├── XSLFPowerPointExtractorDecorator.java │ │ │ │ ├── XSSFBExcelExtractorDecorator.java │ │ │ │ ├── XSSFExcelExtractorDecorator.java │ │ │ │ ├── XWPFListManager.java │ │ │ │ ├── XWPFWordExtractorDecorator.java │ │ │ │ ├── xps │ │ │ │ │ ├── XPSExtractorDecorator.java │ │ │ │ │ ├── XPSPageContentHandler.java │ │ │ │ │ └── XPSTextExtractor.java │ │ │ │ ├── xslf │ │ │ │ │ └── XSLFEventBasedPowerPointExtractor.java │ │ │ │ └── xwpf │ │ │ │ │ ├── XWPFEventBasedWordExtractor.java │ │ │ │ │ ├── XWPFNumberingShim.java │ │ │ │ │ ├── XWPFStylesShim.java │ │ │ │ │ └── ml2006 │ │ │ │ │ ├── AbstractPartHandler.java │ │ │ │ │ ├── BinaryDataHandler.java │ │ │ │ │ ├── CorePropertiesHandler.java │ │ │ │ │ ├── ExtendedPropertiesHandler.java │ │ │ │ │ ├── PartHandler.java │ │ │ │ │ ├── Relationship.java │ │ │ │ │ ├── RelationshipsHandler.java │ │ │ │ │ ├── RelationshipsManager.java │ │ │ │ │ ├── Word2006MLDocHandler.java │ │ │ │ │ ├── Word2006MLParser.java │ │ │ │ │ └── WordAndPowerPointTextPartHandler.java │ │ │ └── xml │ │ │ │ ├── AbstractXML2003Parser.java │ │ │ │ ├── HyperlinkHandler.java │ │ │ │ ├── SpreadsheetMLParser.java │ │ │ │ └── WordMLParser.java │ │ │ ├── mp3 │ │ │ ├── AudioFrame.java │ │ │ ├── CompositeTagHandler.java │ │ │ ├── ID3Tags.java │ │ │ ├── ID3v1Handler.java │ │ │ ├── ID3v22Handler.java │ │ │ ├── ID3v23Handler.java │ │ │ ├── ID3v24Handler.java │ │ │ ├── ID3v2Frame.java │ │ │ ├── LyricsHandler.java │ │ │ ├── MP3Frame.java │ │ │ ├── Mp3Parser.java │ │ │ └── MpegStream.java │ │ │ ├── mp4 │ │ │ ├── ISO6709Extractor.java │ │ │ └── MP4Parser.java │ │ │ ├── ner │ │ │ ├── NERecogniser.java │ │ │ ├── NamedEntityParser.java │ │ │ ├── corenlp │ │ │ │ └── CoreNLPNERecogniser.java │ │ │ ├── grobid │ │ │ │ └── GrobidNERecogniser.java │ │ │ ├── mitie │ │ │ │ └── MITIENERecogniser.java │ │ │ ├── nltk │ │ │ │ └── NLTKNERecogniser.java │ │ │ ├── opennlp │ │ │ │ ├── OpenNLPNERecogniser.java │ │ │ │ └── OpenNLPNameFinder.java │ │ │ └── regex │ │ │ │ └── RegexNERecogniser.java │ │ │ ├── netcdf │ │ │ └── NetCDFParser.java │ │ │ ├── ocr │ │ │ ├── TesseractOCRConfig.java │ │ │ └── TesseractOCRParser.java │ │ │ ├── odf │ │ │ ├── NSNormalizerContentHandler.java │ │ │ ├── OpenDocumentContentParser.java │ │ │ ├── OpenDocumentMetaParser.java │ │ │ └── OpenDocumentParser.java │ │ │ ├── opendocument │ │ │ └── OpenOfficeParser.java │ │ │ ├── pdf │ │ │ ├── AbstractPDF2XHTML.java │ │ │ ├── AccessChecker.java │ │ │ ├── ImageGraphicsEngine.java │ │ │ ├── OCR2XHTML.java │ │ │ ├── PDF2XHTML.java │ │ │ ├── PDFEncodedStringDecoder.java │ │ │ ├── PDFMarkedContent2XHTML.java │ │ │ ├── PDFParser.java │ │ │ ├── PDFParserConfig.java │ │ │ ├── PDFPreflightParser.java │ │ │ ├── PDMetadataExtractor.java │ │ │ └── XFAExtractor.java │ │ │ ├── pkg │ │ │ ├── CompressorParser.java │ │ │ ├── CompressorParserOptions.java │ │ │ ├── PackageParser.java │ │ │ ├── RarParser.java │ │ │ ├── StreamingZipContainerDetector.java │ │ │ ├── ZipContainerDetector.java │ │ │ └── ZipContainerDetectorBase.java │ │ │ ├── pot │ │ │ └── PooledTimeSeriesParser.java │ │ │ ├── prt │ │ │ └── PRTParser.java │ │ │ ├── recognition │ │ │ ├── ObjectRecogniser.java │ │ │ ├── ObjectRecognitionParser.java │ │ │ ├── RecognisedObject.java │ │ │ └── tf │ │ │ │ ├── TensorflowImageRecParser.java │ │ │ │ ├── TensorflowRESTRecogniser.java │ │ │ │ └── TensorflowRESTVideoRecogniser.java │ │ │ ├── rtf │ │ │ ├── GroupState.java │ │ │ ├── ListDescriptor.java │ │ │ ├── RTFEmbObjHandler.java │ │ │ ├── RTFObjDataParser.java │ │ │ ├── RTFParser.java │ │ │ └── TextExtractor.java │ │ │ ├── sas │ │ │ └── SAS7BDATParser.java │ │ │ ├── sentiment │ │ │ └── SentimentAnalysisParser.java │ │ │ ├── strings │ │ │ ├── FileConfig.java │ │ │ ├── Latin1StringsParser.java │ │ │ ├── StringsConfig.java │ │ │ ├── StringsEncoding.java │ │ │ └── StringsParser.java │ │ │ ├── txt │ │ │ ├── CharsetDetector.java │ │ │ ├── CharsetMatch.java │ │ │ ├── CharsetRecog_2022.java │ │ │ ├── CharsetRecog_UTF8.java │ │ │ ├── CharsetRecog_Unicode.java │ │ │ ├── CharsetRecog_mbcs.java │ │ │ ├── CharsetRecog_sbcs.java │ │ │ ├── CharsetRecognizer.java │ │ │ ├── Icu4jEncodingDetector.java │ │ │ ├── TXTParser.java │ │ │ ├── UniversalEncodingDetector.java │ │ │ └── UniversalEncodingListener.java │ │ │ ├── utils │ │ │ ├── BouncyCastleDigester.java │ │ │ ├── CommonsDigester.java │ │ │ ├── DataURIScheme.java │ │ │ ├── DataURISchemeParseException.java │ │ │ ├── DataURISchemeUtil.java │ │ │ └── ZipSalvager.java │ │ │ ├── video │ │ │ └── FLVParser.java │ │ │ ├── wordperfect │ │ │ ├── QPWTextExtractor.java │ │ │ ├── QuattroProParser.java │ │ │ ├── WP5Charsets.java │ │ │ ├── WP5DocumentAreaExtractor.java │ │ │ ├── WP6Charsets.java │ │ │ ├── WP6DocumentAreaExtractor.java │ │ │ ├── WPDocumentAreaExtractor.java │ │ │ ├── WPInputStream.java │ │ │ ├── WPPrefixArea.java │ │ │ ├── WPPrefixAreaExtractor.java │ │ │ └── WordPerfectParser.java │ │ │ ├── xliff │ │ │ ├── XLIFF12ContentHandler.java │ │ │ ├── XLIFF12Parser.java │ │ │ └── XLZParser.java │ │ │ └── xml │ │ │ ├── AbstractMetadataHandler.java │ │ │ ├── AttributeDependantMetadataHandler.java │ │ │ ├── AttributeMetadataHandler.java │ │ │ ├── DcXMLParser.java │ │ │ ├── ElementMetadataHandler.java │ │ │ ├── FictionBookParser.java │ │ │ ├── MetadataHandler.java │ │ │ ├── XMLParser.java │ │ │ └── XMLProfiler.java │ └── resources │ │ ├── META-INF │ │ └── services │ │ │ ├── org.apache.tika.detect.Detector │ │ │ ├── org.apache.tika.detect.EncodingDetector │ │ │ └── org.apache.tika.parser.Parser │ │ └── org │ │ └── apache │ │ └── tika │ │ └── parser │ │ ├── captioning │ │ └── tf │ │ │ ├── caption_generator.py │ │ │ ├── im2txtapi.py │ │ │ ├── model_info.xml │ │ │ ├── model_wrapper.py │ │ │ └── vocabulary.py │ │ ├── ctakes │ │ └── CTAKESConfig.properties │ │ ├── geo │ │ └── topic │ │ │ └── GeoTopicConfig.properties │ │ ├── html │ │ ├── StandardCharsets_unsupported_by_IANA.txt │ │ └── whatwg-encoding-labels.tsv │ │ ├── journal │ │ └── GrobidExtractor.properties │ │ ├── ner │ │ ├── grobid │ │ │ └── GrobidServer.properties │ │ ├── nltk │ │ │ └── NLTKServer.properties │ │ └── regex │ │ │ └── ner-regex.txt │ │ ├── ocr │ │ ├── TesseractOCRConfig.properties │ │ └── rotation.py │ │ ├── pdf │ │ └── PDFParser.properties │ │ └── recognition │ │ └── tf │ │ ├── inception_v4.py │ │ ├── inceptionapi.py │ │ └── video_util.py │ └── test │ ├── java │ └── org │ │ └── apache │ │ └── tika │ │ ├── TestCorruptedFiles.java │ │ ├── TestParsers.java │ │ ├── TestXMLEntityExpansion.java │ │ ├── TestXXEInXML.java │ │ ├── XMLTestBase.java │ │ ├── config │ │ ├── TikaDetectorConfigTest.java │ │ ├── TikaEncodingDetectorTest.java │ │ ├── TikaParserConfigTest.java │ │ └── TikaTranslatorConfigTest.java │ │ ├── detect │ │ └── TestContainerAwareDetector.java │ │ ├── embedder │ │ └── ExternalEmbedderTest.java │ │ ├── extractor │ │ └── EmbeddedDocumentUtilTest.java │ │ ├── mime │ │ ├── MimeTypeTest.java │ │ ├── MimeTypesTest.java │ │ └── TestMimeTypes.java │ │ ├── parser │ │ ├── AutoDetectParserTest.java │ │ ├── AutoDetectReaderParserTest.java │ │ ├── BouncyCastleDigestingParserTest.java │ │ ├── DigestingParserTest.java │ │ ├── ParsingReaderTest.java │ │ ├── RecursiveParserWrapperTest.java │ │ ├── TabularFormatsTest.java │ │ ├── apple │ │ │ └── AppleSingleFileParserTest.java │ │ ├── asm │ │ │ └── ClassParserTest.java │ │ ├── audio │ │ │ ├── AudioParserTest.java │ │ │ └── MidiParserTest.java │ │ ├── chm │ │ │ ├── TestChmBlockInfo.java │ │ │ ├── TestChmExtraction.java │ │ │ ├── TestChmExtractor.java │ │ │ ├── TestChmItsfHeader.java │ │ │ ├── TestChmItspHeader.java │ │ │ ├── TestChmLzxState.java │ │ │ ├── TestChmLzxcControlData.java │ │ │ ├── TestChmLzxcResetTable.java │ │ │ ├── TestDirectoryListingEntry.java │ │ │ ├── TestParameters.java │ │ │ ├── TestPmgiHeader.java │ │ │ └── TestPmglHeader.java │ │ ├── code │ │ │ └── SourceCodeParserTest.java │ │ ├── crypto │ │ │ ├── Pkcs7ParserTest.java │ │ │ └── TSDParserTest.java │ │ ├── csv │ │ │ ├── CSVSnifferTest.java │ │ │ └── TextAndCSVParserTest.java │ │ ├── dbf │ │ │ └── DBFParserTest.java │ │ ├── dif │ │ │ └── DIFParserTest.java │ │ ├── dwg │ │ │ └── DWGParserTest.java │ │ ├── envi │ │ │ └── EnviHeaderParserTest.java │ │ ├── epub │ │ │ └── EpubParserTest.java │ │ ├── executable │ │ │ └── ExecutableParserTest.java │ │ ├── feed │ │ │ └── FeedParserTest.java │ │ ├── font │ │ │ └── FontParsersTest.java │ │ ├── fork │ │ │ └── ForkParserIntegrationTest.java │ │ ├── gdal │ │ │ └── TestGDALParser.java │ │ ├── geo │ │ │ └── topic │ │ │ │ └── GeoParserTest.java │ │ ├── geoinfo │ │ │ └── GeographicInformationParserTest.java │ │ ├── grib │ │ │ └── GribParserTest.java │ │ ├── hdf │ │ │ └── HDFParserTest.java │ │ ├── html │ │ │ ├── HtmlEncodingDetectorTest.java │ │ │ ├── HtmlParserTest.java │ │ │ └── StandardHtmlEncodingDetectorTest.java │ │ ├── hwp │ │ │ └── HwpV5ParserTest.java │ │ ├── ibooks │ │ │ └── iBooksParserTest.java │ │ ├── image │ │ │ ├── BPGParserTest.java │ │ │ ├── ICNSParserTest.java │ │ │ ├── ImageMetadataExtractorTest.java │ │ │ ├── ImageParserTest.java │ │ │ ├── MetadataFieldsTest.java │ │ │ ├── PSDParserTest.java │ │ │ ├── TiffParserTest.java │ │ │ ├── WebPParserTest.java │ │ │ └── xmp │ │ │ │ └── JempboxExtractorTest.java │ │ ├── isatab │ │ │ └── ISArchiveParserTest.java │ │ ├── iwork │ │ │ ├── AutoPageNumberUtilsTest.java │ │ │ ├── IWorkParserTest.java │ │ │ └── iwana │ │ │ │ └── IWork13ParserTest.java │ │ ├── jdbc │ │ │ └── SQLite3ParserTest.java │ │ ├── journal │ │ │ ├── JournalParserTest.java │ │ │ └── TEITest.java │ │ ├── jpeg │ │ │ └── JpegParserTest.java │ │ ├── mail │ │ │ ├── MailUtilTest.java │ │ │ └── RFC822ParserTest.java │ │ ├── mat │ │ │ └── MatParserTest.java │ │ ├── mbox │ │ │ ├── MboxParserTest.java │ │ │ └── OutlookPSTParserTest.java │ │ ├── microsoft │ │ │ ├── AbstractPOIContainerExtractionTest.java │ │ │ ├── EMFParserTest.java │ │ │ ├── ExcelParserTest.java │ │ │ ├── JackcessParserTest.java │ │ │ ├── MSOwnerFileParserTest.java │ │ │ ├── OfficeParserTest.java │ │ │ ├── OldExcelParserTest.java │ │ │ ├── OutlookParserTest.java │ │ │ ├── POIContainerExtractionTest.java │ │ │ ├── PowerPointParserTest.java │ │ │ ├── ProjectParserTest.java │ │ │ ├── PublisherParserTest.java │ │ │ ├── TNEFParserTest.java │ │ │ ├── VisioParserTest.java │ │ │ ├── WMFParserTest.java │ │ │ ├── WordParserTest.java │ │ │ ├── WriteProtectedParserTest.java │ │ │ ├── onenote │ │ │ │ └── OneNoteParserTest.java │ │ │ ├── ooxml │ │ │ │ ├── OOXMLContainerExtractionTest.java │ │ │ │ ├── OOXMLParserTest.java │ │ │ │ ├── SXSLFExtractorTest.java │ │ │ │ ├── SXWPFExtractorTest.java │ │ │ │ ├── TruncatedOOXMLTest.java │ │ │ │ ├── xps │ │ │ │ │ └── XPSParserTest.java │ │ │ │ └── xwpf │ │ │ │ │ └── ml2006 │ │ │ │ │ └── Word2006MLParserTest.java │ │ │ └── xml │ │ │ │ └── XML2003ParserTest.java │ │ ├── mock │ │ │ └── MockParserTest.java │ │ ├── mp3 │ │ │ ├── Mp3ParserTest.java │ │ │ └── MpegStreamTest.java │ │ ├── mp4 │ │ │ ├── ISO6709ExtractorTest.java │ │ │ └── MP4ParserTest.java │ │ ├── ner │ │ │ ├── NamedEntityParserTest.java │ │ │ ├── nltk │ │ │ │ └── NLTKNERecogniserTest.java │ │ │ └── regex │ │ │ │ └── RegexNERecogniserTest.java │ │ ├── netcdf │ │ │ └── NetCDFParserTest.java │ │ ├── ocr │ │ │ ├── TesseractOCRConfigTest.java │ │ │ └── TesseractOCRParserTest.java │ │ ├── odf │ │ │ └── ODFParserTest.java │ │ ├── pdf │ │ │ ├── AccessCheckerTest.java │ │ │ ├── PDFMarkedContent2XHTMLTest.java │ │ │ ├── PDFParserTest.java │ │ │ └── PDFPreflightParserTest.java │ │ ├── pkg │ │ │ ├── AbstractPkgTest.java │ │ │ ├── ArParserTest.java │ │ │ ├── Bzip2ParserTest.java │ │ │ ├── CompressParserTest.java │ │ │ ├── CompressorParserTest.java │ │ │ ├── GzipParserTest.java │ │ │ ├── PackageParserTest.java │ │ │ ├── RarParserTest.java │ │ │ ├── Seven7ParserTest.java │ │ │ ├── TarParserTest.java │ │ │ ├── ZipContainerDetectorTest.java │ │ │ ├── ZipParserTest.java │ │ │ └── ZlibParserTest.java │ │ ├── prt │ │ │ └── PRTParserTest.java │ │ ├── recognition │ │ │ ├── ObjectRecognitionParserTest.java │ │ │ └── tf │ │ │ │ ├── TensorflowImageRecParserTest.java │ │ │ │ └── TensorflowVideoRecParserTest.java │ │ ├── rtf │ │ │ └── RTFParserTest.java │ │ ├── sas │ │ │ └── SAS7BDATParserTest.java │ │ ├── sentiment │ │ │ └── SentimentAnalysisParserTest.java │ │ ├── solidworks │ │ │ └── SolidworksParserTest.java │ │ ├── strings │ │ │ ├── FileConfigTest.java │ │ │ ├── Latin1StringsParserTest.java │ │ │ ├── StringsConfigTest.java │ │ │ └── StringsParserTest.java │ │ ├── txt │ │ │ ├── CharsetDetectorTest.java │ │ │ └── TXTParserTest.java │ │ ├── utils │ │ │ └── DataURISchemeParserTest.java │ │ ├── video │ │ │ └── FLVParserTest.java │ │ ├── wordperfect │ │ │ ├── QuattroProTest.java │ │ │ ├── WPInputStreamTest.java │ │ │ └── WordPerfectTest.java │ │ ├── xliff │ │ │ ├── XLIFF12ParserTest.java │ │ │ └── XLZParserTest.java │ │ └── xml │ │ │ ├── DcXMLParserTest.java │ │ │ ├── EmptyAndDuplicateElementsXMLParserTest.java │ │ │ └── FictionBookParserTest.java │ │ ├── sax │ │ ├── PhoneExtractingContentHandlerTest.java │ │ └── StandardsExtractingContentHandlerTest.java │ │ └── utils │ │ └── ServiceLoaderUtilsTest.java │ └── resources │ ├── log4j.properties │ ├── org │ └── apache │ │ └── tika │ │ ├── config │ │ ├── TIKA-1558-blacklist.xml │ │ ├── TIKA-1558-blacklistsub.xml │ │ ├── TIKA-1702-detector-blacklist.xml │ │ ├── TIKA-1702-translator-default.xml │ │ ├── TIKA-1702-translator-empty-default.xml │ │ ├── TIKA-1702-translator-empty.xml │ │ ├── TIKA-1708-detector-composite.xml │ │ ├── TIKA-1708-detector-default.xml │ │ ├── TIKA-2273-blacklist-encoding-detector-default.xml │ │ ├── TIKA-2273-encoding-detector-outside-static-init.xml │ │ ├── TIKA-2273-no-icu4j-encoding-detector.xml │ │ ├── TIKA-2273-non-detecting-params-bad-charset.xml │ │ ├── TIKA-2273-non-detecting-params.xml │ │ ├── TIKA-2273-parameterize-encoding-detector.xml │ │ ├── TIKA-2485-encoding-detector-mark-limits.xml │ │ ├── TIKA-2705-tesseract.xml │ │ └── TIKA-3078-geo.topic.GeoParser.xml │ │ └── parser │ │ ├── csv │ │ └── tika-config.xml │ │ ├── epub │ │ └── tika-config.xml │ │ ├── html │ │ └── tika-config.xml │ │ ├── mail │ │ └── tika-config-extract-all-alternatives.xml │ │ ├── microsoft │ │ ├── ooxml │ │ │ ├── tika-config-custom-date-override.xml │ │ │ ├── tika-config-dom-macros.xml │ │ │ └── tika-config-sax-macros.xml │ │ ├── tika-config-custom-date-override.xml │ │ ├── tika-config-exclude-phonetic.xml │ │ ├── tika-config-extract-all-alternatives-msg.xml │ │ ├── tika-config-macros.xml │ │ └── tika-config-sax-docx.xml │ │ ├── ner │ │ ├── opennlp │ │ │ ├── ModelGetter.groovy │ │ │ └── get-models.sh │ │ ├── regex │ │ │ └── ner-regex.txt │ │ └── tika-config.xml │ │ ├── pdf │ │ ├── tika-config-non-primitives.xml │ │ ├── tika-config.xml │ │ ├── tika-inline-config.xml │ │ ├── tika-ocr-config.xml │ │ ├── tika-preflight-config.xml │ │ └── tika-xml-profiler-config.xml │ │ ├── pkg │ │ └── tika-config.xml │ │ ├── recognition │ │ ├── tika-config-tflow-im2txt-rest.xml │ │ ├── tika-config-tflow-rest.xml │ │ ├── tika-config-tflow-video-rest.xml │ │ └── tika-config-tflow.xml │ │ ├── rtf │ │ ├── ignoreListMarkup-tika-config.xml │ │ └── tika-config.xml │ │ ├── sentiment │ │ ├── tika-config-sentiment-opennlp-cat.xml │ │ └── tika-config-sentiment-opennlp.xml │ │ └── wordperfect │ │ └── tika-config.xml │ ├── test-documents │ ├── AppleSingleFileParser.class │ ├── AutoDetectParser.class │ ├── Doc1_ole.doc │ ├── EmbeddedDocument.docx │ ├── EmbeddedOutlook.docx │ ├── EmbeddedPDF.docx │ ├── GLDAS_CLM10SUBP_3H.A19790202.0000.001.grb │ ├── MANIFEST.XML.TSD │ ├── NUTCH-1997.cbor │ ├── NullHeader.docx │ ├── TIKA-216.tgz │ ├── Test1.txt.tsd │ ├── Test2.txt.tsd │ ├── Test3.docx.tsd │ ├── Test4.pdf.tsd │ ├── Test5.PNG.tsd │ ├── WFPC2u5780205r_c0fx.fits │ ├── Zamora2010.dif │ ├── active_layer_arcss_grid_barrow_alaska_2012.dif │ ├── baseball.gif │ ├── baseball.jpg │ ├── baseball.png │ ├── big-preamble.html │ ├── boilerplate-whitespace.html │ ├── boilerplate.html │ ├── breidamerkurjokull_radar_profiles_2009.mat │ ├── carbon_isotopic_values_of_alkanes_extracted_from_paleosols.dif │ ├── chm │ │ ├── IMJPCL.CHM │ │ ├── IMJPCLE.CHM │ │ ├── IMTCEN.CHM │ │ ├── admin.chm │ │ ├── cmak_ops.CHM │ │ ├── comexp.CHM │ │ ├── gpedit.CHM │ │ ├── tcpip.CHM │ │ └── wmicontrol.CHM │ ├── complex.mbox │ ├── droste.zip │ ├── egyl03.gdas.200811.00Z.grb2 │ ├── english.cp500.txt │ ├── envi_test_header.hdr │ ├── footnotes.docx │ ├── full_encrypted.7z │ ├── gdas1.forecmwf.2014062612.grib2 │ ├── headerPic.docx │ ├── headers.mbox │ ├── jxl.xls │ ├── moby.zip │ ├── mock │ │ ├── embedded_then_npe.xml │ │ ├── example.xml │ │ ├── fake_oom.xml │ │ ├── heavy_hang.xml │ │ ├── nothing_bad.xml │ │ ├── null_pointer.xml │ │ ├── null_pointer_no_msg.xml │ │ ├── real_oom.xml │ │ ├── sleep.xml │ │ ├── sleep_interruptible.xml │ │ ├── sleep_not_interruptible.xml │ │ ├── system_exit.xml │ │ └── thread_interrupt.xml │ ├── multi-language.txt │ ├── multiline.mbox │ ├── pictures.ppt │ ├── protect.xlsx │ ├── protectedFile.xlsx │ ├── protectedSheets.xlsx │ ├── quine.gz │ ├── quoted.mbox │ ├── resume.html │ ├── rsstest_091.rss │ ├── rsstest_20.rss │ ├── russian.cp866.txt │ ├── sampleFile.iso19139 │ ├── simple.mbox │ ├── single_mail.mbox │ ├── sresa1b_ncar_ccsm3_0_run1_200001.nc │ ├── tableHeaders.numbers │ ├── tableNames.numbers │ ├── test-columnar.csv │ ├── test-columnar.ods │ ├── test-columnar.sas.xml │ ├── test-columnar.sas7bdat │ ├── test-columnar.xls │ ├── test-columnar.xlsb │ ├── test-columnar.xlsx │ ├── test-columnar.xpt │ ├── test-documents-enc.rar │ ├── test-documents-spanned.z01 │ ├── test-documents-spanned.zip │ ├── test-documents.7z │ ├── test-documents.cab │ ├── test-documents.cpio │ ├── test-documents.ddf │ ├── test-documents.dmg │ ├── test-documents.rar │ ├── test-documents.tar │ ├── test-documents.tar.Z │ ├── test-documents.tbz2 │ ├── test-documents.tgz │ ├── test-documents.zip │ ├── test-outlook.msg │ ├── test-outlook2003.msg │ ├── test-zip-of-zip.zip │ ├── test.doc │ ├── test.fb2 │ ├── test.hdf │ ├── test.he5 │ ├── test1.swf │ ├── test2.swf │ ├── test3.swf │ ├── test7Z_protected_passTika.7z │ ├── testACCESS.mdb │ ├── testAFM.afm │ ├── testAIFF.aif │ ├── testAMR-WB.amr │ ├── testAMR.amr │ ├── testAPK.apk │ ├── testARofSND.ar │ ├── testARofText.ar │ ├── testASF.asf │ ├── testASiCE.asice │ ├── testASiCS.asics │ ├── testATOM.atom │ ├── testAU.au │ ├── testAccess2.accdb │ ├── testAccess2_2000.mdb │ ├── testAccess2_2002-2003.mdb │ ├── testAccess2_encrypted.accdb │ ├── testAccess_V1997.mdb │ ├── testAnnotations.pdf │ ├── testAppleSingleFile.pdf │ ├── testBAT.bat │ ├── testBATUpper.bat │ ├── testBDB_btree_2.db │ ├── testBDB_btree_3.db │ ├── testBDB_btree_4.db │ ├── testBDB_btree_5.db │ ├── testBDB_hash_2.db │ ├── testBDB_hash_3.db │ ├── testBDB_hash_4.db │ ├── testBDB_hash_5.db │ ├── testBIBTEX.bib │ ├── testBMP.bmp │ ├── testBMPfp.txt │ ├── testBPG.bpg │ ├── testBPG_GEO.bpg │ ├── testBPG_commented.bpg │ ├── testBPG_commented_xnviewmp026.bpg │ ├── testBROTLI_compressed.br │ ├── testBinControlWord.rtf │ ├── testBulletPoints.key │ ├── testC.c │ ├── testCADKEY.prt │ ├── testCADKEY2.prt │ ├── testCOREL.shw │ ├── testCPP.cpp │ ├── testCSS.css │ ├── testCSV.csv │ ├── testChm.chm │ ├── testChm2.chm │ ├── testChm3.chm │ ├── testChm_oom.chm │ ├── testComment.doc │ ├── testComment.docx │ ├── testComment.pdf │ ├── testComment.ppt │ ├── testComment.pptx │ ├── testComment.rtf │ ├── testComment.xls │ ├── testComment.xlsx │ ├── testControlCharacters.doc │ ├── testDBF.dbf │ ├── testDBF_gb18030.dbf │ ├── testDCX.dcx │ ├── testDITA.dita │ ├── testDITA.ditamap │ ├── testDITA2.dita │ ├── testDJVU.djvu │ ├── testDOCX_Thumbnail.docx │ ├── testDOTM.dotm │ ├── testDWF2010.dwf │ ├── testDWG2000.dwg │ ├── testDWG2004.dwg │ ├── testDWG2004_no_header.dwg │ ├── testDWG2007.dwg │ ├── testDWG2010.dwg │ ├── testDWG2010_custom_props.dwg │ ├── testDWGmech2004.dwg │ ├── testDWGmech2004DX.dwg │ ├── testDWGmech2005.dwg │ ├── testDWGmech2006.dwg │ ├── testDWGmech2007.dwg │ ├── testDWGmech2008.dwg │ ├── testDWGmech2009.dwg │ ├── testDWGmech2010.dwg │ ├── testDWGmech2011.dwg │ ├── testDWGmech6.dwg │ ├── testDXF_ascii.dxf │ ├── testDetached.p7s │ ├── testDigilite.fdf │ ├── testDocumentLink.doc │ ├── testEAR.ear │ ├── testEMF.emf │ ├── testEMLX.emlx │ ├── testEML_embedded_xhtml_and_img.eml │ ├── testEPUB.epub │ ├── testEPUB_xml_ext.epub │ ├── testEXCEL-charts.xls │ ├── testEXCEL-formats.xls │ ├── testEXCEL-formats.xlsx │ ├── testEXCEL.strict.xlsx │ ├── testEXCEL.xls │ ├── testEXCEL.xlsb │ ├── testEXCEL.xlsx │ ├── testEXCEL2003.xml │ ├── testEXCEL_1img.xls │ ├── testEXCEL_1img.xlsx │ ├── testEXCEL_4.xls │ ├── testEXCEL_5.xls │ ├── testEXCEL_95.xls │ ├── testEXCEL_WORKBOOK_in_capitals.xls │ ├── testEXCEL_big_numbers.xls │ ├── testEXCEL_big_numbers.xlsx │ ├── testEXCEL_charts.xlsb │ ├── testEXCEL_charts.xlsx │ ├── testEXCEL_custom_props.xls │ ├── testEXCEL_custom_props.xlsx │ ├── testEXCEL_dateFormats.xls │ ├── testEXCEL_dateFormats.xlsx │ ├── testEXCEL_diagramData.xlsb │ ├── testEXCEL_diagramData.xlsx │ ├── testEXCEL_embeddedPDF_mac.xls │ ├── testEXCEL_embeddedPDF_mac.xlsx │ ├── testEXCEL_embeddedPDF_windows.xls │ ├── testEXCEL_embeddedPDF_windows.xlsx │ ├── testEXCEL_embeded.xls │ ├── testEXCEL_embeded.xlsx │ ├── testEXCEL_headers_footers.xls │ ├── testEXCEL_headers_footers.xlsx │ ├── testEXCEL_hyperlinks.xls │ ├── testEXCEL_hyperlinks.xlsx │ ├── testEXCEL_labels-govdocs-515858.xls │ ├── testEXCEL_macro.xls │ ├── testEXCEL_macro.xlsm │ ├── testEXCEL_macro_enabled_template.xltm │ ├── testEXCEL_phonetic.xls │ ├── testEXCEL_phonetic.xlsx │ ├── testEXCEL_poi-61034.xlsx │ ├── testEXCEL_poi.xlsx │ ├── testEXCEL_protected_passtika.xls │ ├── testEXCEL_protected_passtika.xlsx │ ├── testEXCEL_protected_passtika_2.xlsx │ ├── testEXCEL_signed.xlsx │ ├── testEXCEL_template.xlt │ ├── testEXCEL_template.xltx │ ├── testEXCEL_textbox.xls │ ├── testEXCEL_textbox.xlsx │ ├── testEXCEL_various.xlsb │ ├── testEmailWithPNGAtt.eml │ ├── testEmbedded.zip │ ├── testEndNoteImportFile.enw │ ├── testExcel_embeddedPDF.xls │ ├── testExcel_embeddedPDF.xlsx │ ├── testException1.doc │ ├── testException2.doc │ ├── testExtraSpaces.pdf │ ├── testFITS.fits │ ├── testFITS_ShorterHeader.fits │ ├── testFLAC.flac │ ├── testFLAC.oga │ ├── testFLV.flv │ ├── testFOXMAIL.box │ ├── testFontAfterBufferedText.rtf │ ├── testFooter.ods │ ├── testFooter.odt │ ├── testFreeBSD-x86-64 │ ├── testGIF.gif │ ├── testGRAPHVIZd.dot │ ├── testGRAPHVIZdc.dot │ ├── testGRAPHVIZg.dot │ ├── testGROOVY.groovy │ ├── testGroupWiseEml.eml │ ├── testH.h │ ├── testHEIF.heic │ ├── testHFA.hfa │ ├── testHTML.html │ ├── testHTMLBadScript.html │ ├── testHTMLGoodScript.html │ ├── testHTMLNoisyMetaEncoding_1.html │ ├── testHTMLNoisyMetaEncoding_2.html │ ├── testHTMLNoisyMetaEncoding_3.html │ ├── testHTMLNoisyMetaEncoding_4.html │ ├── testHTML_charset_utf16le.html │ ├── testHTML_charset_utf8.html │ ├── testHTML_embedded_data_uri_js.html │ ├── testHTML_embedded_img.html │ ├── testHTML_embedded_img_in_js.html │ ├── testHTML_head.html │ ├── testHTML_utf8.html │ ├── testHWP-v5-dist.hwp │ ├── testHWP-v5b.hwp │ ├── testHWP_3.0.hwp │ ├── testHWP_5.0.hwp │ ├── testICNS.icns │ ├── testICNS_basic.icns │ ├── testICalendar.ics │ ├── testINDD.indd │ ├── testIPA.ipa │ ├── testISATab_BII-I-1 │ │ ├── a_bii-s-2_metabolite profiling_NMR spectroscopy.txt │ │ ├── a_metabolome.txt │ │ ├── a_microarray.txt │ │ ├── a_proteome.txt │ │ ├── a_transcriptome.txt │ │ ├── i_investigation.txt │ │ ├── s_BII-S-1.txt │ │ └── s_BII-S-2.txt │ ├── testJAR.jar │ ├── testJAR_with_HTML.jar │ ├── testJAR_with_PEHDR.jar │ ├── testJAVA.java │ ├── testJAVAPROPS.properties │ ├── testJBIG2.jb2 │ ├── testJNILIB.jnilib │ ├── testJPEG.jp2 │ ├── testJPEG.jpg │ ├── testJPEG_EXIF.jpg │ ├── testJPEG_EXIF_emptyDateTime.jpg │ ├── testJPEG_GEO.jpg │ ├── testJPEG_GEO_2.jpg │ ├── testJPEG_commented.jpg │ ├── testJPEG_commented_pspcs2mac.jpg │ ├── testJPEG_commented_xnviewmp026.jpg │ ├── testJPEG_oddTagComponent.jpg │ ├── testJS.js │ ├── testJS_HTML.js │ ├── testJournalParser.pdf │ ├── testKML.kml │ ├── testKMZ.kmz │ ├── testKeynote.key │ ├── testKeynote2013.key │ ├── testKeynote2018.key │ ├── testLZ4-framed.lz4 │ ├── testLZMA_oom │ ├── testLinux-arm-32le │ ├── testLinux-mips-32be │ ├── testLinux-mips-32le │ ├── testLinux-ppc-32be │ ├── testLinux-x86-32 │ ├── testLinux-x86-64 │ ├── testLotusEml.eml │ ├── testMATLAB.m │ ├── testMATLAB_barcast.m │ ├── testMATLAB_wtsgaus.m │ ├── testMBOX_complex.mbox │ ├── testMBOX_lengthy_x-headers.mbox │ ├── testMHTMLFirefox.mhtml │ ├── testMID.mid │ ├── testMIF.mif │ ├── testMKV.mkv │ ├── testMP3i18n.mp3 │ ├── testMP3i18n_truncated.mp3 │ ├── testMP3id3v1.mp3 │ ├── testMP3id3v1_v2.mp3 │ ├── testMP3id3v2.mp3 │ ├── testMP3id3v24.mp3 │ ├── testMP3lyrics.mp3 │ ├── testMP3noid3.mp3 │ ├── testMP3truncated.mp3 │ ├── testMP4.m4a │ ├── testMP4_truncated.m4a │ ├── testMSChart-govdocs-428996.ppt │ ├── testMSChart-govdocs-428996.pptx │ ├── testMSChart-govdocs-428996.xls │ ├── testMSChart-govdocs-428996.xlsx │ ├── testMSEquation-govdocs-863534.doc │ ├── testMSG.msg │ ├── testMSG_Appointment.msg │ ├── testMSG_Contact.msg │ ├── testMSG_Post.msg │ ├── testMSG_StickyNote.msg │ ├── testMSG_Task.msg │ ├── testMSG_att_doc.msg │ ├── testMSG_att_msg.msg │ ├── testMSG_chinese.msg │ ├── testMSG_forwarded.msg │ ├── testMSOwnerFile │ ├── testMSWriteFile.wri │ ├── testMYSQL.MYD │ ├── testMYSQL.MYI │ ├── testMYSQL.frm │ ├── testMasterFooter.odp │ ├── testMasterSlideTable.key │ ├── testMessageNews.txt │ ├── testNLS1.nls │ ├── testNLS2.nls │ ├── testNPEOpenDocument.odt │ ├── testNakedUTF16BOM.mp3 │ ├── testNumbers.numbers │ ├── testNumbers2013.numbers │ ├── testNumbersCharts.numbers │ ├── testOCR.docx │ ├── testOCR.jpg │ ├── testOCR.pdf │ ├── testOCR.pptx │ ├── testOCR_spacing.png │ ├── testOCTET_header.dbase3 │ ├── testODFwithOOo3.odt │ ├── testODT-TIKA-6000.odt │ ├── testODTEmbedded.odt │ ├── testODTNoMeta.odt │ ├── testODTStyles2.odt │ ├── testODTStyles3.odt │ ├── testODTnotaZipFile.odt │ ├── testOPUS.opus │ ├── testOneNote.one │ ├── testOneNote1.one │ ├── testOneNote2.one │ ├── testOneNote2007OrEarlier1.one │ ├── testOneNote2007OrEarlier2.one │ ├── testOneNote2016.one │ ├── testOneNote3.one │ ├── testOneNote4.one │ ├── testOneNoteEmbeddedWordDoc.one │ ├── testOpenOffice-autotext.bau │ ├── testOpenOffice-extension.oxt │ ├── testOpenOffice2.odf │ ├── testOpenOffice2.odt │ ├── testOpenOfficeInAZip.zip │ ├── testOptionalHyphen.doc │ ├── testOptionalHyphen.docx │ ├── testOptionalHyphen.pdf │ ├── testOptionalHyphen.ppt │ ├── testOptionalHyphen.pptx │ ├── testOptionalHyphen.rtf │ ├── testOverlappingText.pdf │ ├── testPBM.pbm │ ├── testPCX.pcx │ ├── testPDF-custommetadata.pdf │ ├── testPDF.pdf │ ├── testPDFEmbeddingAndEmbedded.docx │ ├── testPDFFileEmbInAnnotation.pdf │ ├── testPDFFileEmbInAnnotation_noContents.pdf │ ├── testPDFPackage.pdf │ ├── testPDFTripleLangTitle.pdf │ ├── testPDFTwoTextBoxes.pdf │ ├── testPDFVarious.pdf │ ├── testPDF_1x_metadata.pdf │ ├── testPDF_JBIG2.pdf │ ├── testPDF_PDFEncodedStringInXMP.pdf │ ├── testPDF_Version.10.x.pdf │ ├── testPDF_Version.11.x.PDFA-1b.pdf │ ├── testPDF_Version.4.x.pdf │ ├── testPDF_Version.5.x.pdf │ ├── testPDF_Version.6.x.pdf │ ├── testPDF_Version.7.x.pdf │ ├── testPDF_Version.8.x.pdf │ ├── testPDF_Version.9.x.pdf │ ├── testPDF_XFA_govdocs1_258578.pdf │ ├── testPDF_acroform3.pdf │ ├── testPDF_angles.pdf │ ├── testPDF_bad_page_303226.pdf │ ├── testPDF_bom.pdf │ ├── testPDF_bookmarks.pdf │ ├── testPDF_childAttachments.pdf │ ├── testPDF_diffTitles.pdf │ ├── testPDF_multiFormatEmbFiles.pdf │ ├── testPDF_no_extract_no_accessibility_owner_empty.pdf │ ├── testPDF_no_extract_no_accessibility_owner_user.pdf │ ├── testPDF_no_extract_yes_accessibility_owner_empty.pdf │ ├── testPDF_no_extract_yes_accessibility_owner_user.pdf │ ├── testPDF_protected.pdf │ ├── testPDF_twoAuthors.pdf │ ├── testPGM.pgm │ ├── testPICT.pct │ ├── testPKCS17Sig-v2.xml.p7m │ ├── testPKCS17Sig-v3.xml.p7m │ ├── testPKCS17Sig-v4.xml.p7m │ ├── testPKCS17Sig.xml.p7m │ ├── testPNG.png │ ├── testPPM.ppm │ ├── testPPT.potm │ ├── testPPT.ppsm │ ├── testPPT.ppsx │ ├── testPPT.ppt │ ├── testPPT.pptm │ ├── testPPT.pptx │ ├── testPPT.thmx │ ├── testPPT.xps │ ├── testPPTX_Thumbnail.pptx │ ├── testPPTX_overlappingRelations.pptx │ ├── testPPT_2imgs.ppt │ ├── testPPT_2imgs.pptx │ ├── testPPT_EmbeddedPDF.ppt │ ├── testPPT_EmbeddedPDF.pptx │ ├── testPPT_autodate.ppt │ ├── testPPT_autodate.pptx │ ├── testPPT_charts.pptx │ ├── testPPT_comment.ppt │ ├── testPPT_comment.pptx │ ├── testPPT_custom_props.ppt │ ├── testPPT_custom_props.pptx │ ├── testPPT_diagramData.pptx │ ├── testPPT_embedded2.ppt │ ├── testPPT_embeddedMP3.pptx │ ├── testPPT_embedded_two_slides.pptx │ ├── testPPT_embeded.ppt │ ├── testPPT_embeded.pptx │ ├── testPPT_groups.ppt │ ├── testPPT_groups.pptx │ ├── testPPT_macros.ppt │ ├── testPPT_macros.pptm │ ├── testPPT_masterFooter.ppt │ ├── testPPT_masterFooter.pptx │ ├── testPPT_masterText.ppt │ ├── testPPT_masterText.pptx │ ├── testPPT_masterText2.ppt │ ├── testPPT_masterText2.pptx │ ├── testPPT_oleWorkbook.ppt │ ├── testPPT_oleWorkbook.pptx │ ├── testPPT_protected_passtika.ppt │ ├── testPPT_protected_passtika.pptx │ ├── testPPT_signed.pptx │ ├── testPPT_skipBadCompressedObject.ppt │ ├── testPPT_various.ppt │ ├── testPPT_various.pptx │ ├── testPPT_various2.pptx │ ├── testPROJECT2003.mpp │ ├── testPROJECT2007.mpp │ ├── testPSD.psd │ ├── testPSD2.psd │ ├── testPSD_xmp.psd │ ├── testPST.pst │ ├── testPST_variousBodyTypes.pst │ ├── testPUBLISHER.pub │ ├── testPageNumber.pdf │ ├── testPages.pages │ ├── testPages2013.pages │ ├── testPagesComments.pages │ ├── testPagesHeadersFootersAlphaLower.pages │ ├── testPagesHeadersFootersAlphaUpper.pages │ ├── testPagesHeadersFootersFootnotes.pages │ ├── testPagesHeadersFootersRomanLower.pages │ ├── testPagesHeadersFootersRomanUpper.pages │ ├── testPagesLayout.pages │ ├── testPagesPwdProtected.pages │ ├── testPhoneNumberExtractor.odt │ ├── testPopupAnnotation.pdf │ ├── testQUATTRO.qpw │ ├── testQUATTRO.wb3 │ ├── testRDF.rdf │ ├── testRFC822 │ ├── testRFC822-CC-BCC │ ├── testRFC822-big │ ├── testRFC822-limitedheaders │ ├── testRFC822-mixed-simple │ ├── testRFC822-mixed-with-pdf-inline │ ├── testRFC822-multipart │ ├── testRFC822-txt-body │ ├── testRFC822_base64 │ ├── testRFC822_date_utf8 │ ├── testRFC822_dkim.eml │ ├── testRFC822_eml │ ├── testRFC822_encrypted_zip │ ├── testRFC822_i18nheaders │ ├── testRFC822_normal_zip │ ├── testRFC822_oddfrom │ ├── testRFC822_quoted │ ├── testRFC822_simple_inline_body.txt │ ├── testRFC822_x-.eml │ ├── testRTF-ms932.rtf │ ├── testRTF.rtf │ ├── testRTFBoldItalic.rtf │ ├── testRTFBoldPlain.rtf │ ├── testRTFControls.rtf │ ├── testRTFCorruptListOverride.rtf │ ├── testRTFEmbeddedFiles.rtf │ ├── testRTFEmbeddedLink.rtf │ ├── testRTFHexEscapeInsideWord.rtf │ ├── testRTFHyperlink.rtf │ ├── testRTFIgnoredControlWord.rtf │ ├── testRTFInvalidUnicode.rtf │ ├── testRTFJapanese.rtf │ ├── testRTFListLibreOffice.rtf │ ├── testRTFListMicrosoftWord.rtf │ ├── testRTFListOverride.rtf │ ├── testRTFNewlines.rtf │ ├── testRTFRegularImages.rtf │ ├── testRTFTIKA_1713.rtf │ ├── testRTFTIKA_2150.rtf │ ├── testRTFTIKA_2500.rtf │ ├── testRTFTIKA_2883.rtf │ ├── testRTFTIKA_2899.rtf │ ├── testRTFTableCellSeparation.rtf │ ├── testRTFTableCellSeparation2.rtf │ ├── testRTFUmlautSpaces.rtf │ ├── testRTFUmlautSpaces2.rtf │ ├── testRTFUnicodeGothic.rtf │ ├── testRTFUnicodeUCNControlWordCharacterDoubling.rtf │ ├── testRTFVarious.rtf │ ├── testRTFWindowsCodepage1250.rtf │ ├── testRTFWithCurlyBraces.rtf │ ├── testRTFWord2010CzechCharacters.rtf │ ├── testRTFWordPadCzechCharacters.rtf │ ├── testRTF_annotation_spacing.rtf │ ├── testRotated.png │ ├── testSAS.sas │ ├── testSAS.sas7bdat │ ├── testSAS.sd2 │ ├── testSAS.xpt │ ├── testSAS2.sas │ ├── testSQLITE3.db │ ├── testSVG.svg │ ├── testSVG.svgz │ ├── testSnappy-framed.sz │ ├── testSolaris-x86-32 │ ├── testSqlite3b.db │ ├── testStandardsExtractor.pdf │ ├── testStarOffice-5.2-calc.sdc │ ├── testStarOffice-5.2-draw.sda │ ├── testStarOffice-5.2-impress.sdd │ ├── testStarOffice-5.2-writer.sdw │ ├── testStarOffice-6.0-calc.sxc │ ├── testStarOffice-6.0-draw.sxd │ ├── testStarOffice-6.0-draw.sxi │ ├── testStarOffice-6.0-writer-template.stw │ ├── testStarOffice-6.0-writer.sxw │ ├── testStataDTA.dta │ ├── testStataDTA.txt │ ├── testStyles.odt │ ├── testTAR_no_magic.tar │ ├── testTEI.xml │ ├── testTIFF.tif │ ├── testTIFF_multipage.tif │ ├── testTSD_broken_pdf.tsd │ ├── testTXT-tika.axx │ ├── testTXT.txt │ ├── testTXT.zlib │ ├── testTXT.zlib0 │ ├── testTXT.zlib5 │ ├── testTXT.zlib9 │ ├── testTXTNonASCIIUTF8.txt │ ├── testTXT_win-1252.txt │ ├── testTables.key │ ├── testTextBoxes.key │ ├── testThunderbirdEml.eml │ ├── testTinyPE.exe │ ├── testTrueType3.ttf │ ├── testUserDefinedCharset.mhtml │ ├── testVCalendar.vcs │ ├── testVISIO.vsd │ ├── testVISIO.vsdm │ ├── testVISIO.vsdx │ ├── testVISIO.vssm │ ├── testVISIO.vssx │ ├── testVISIO.vstm │ ├── testVISIO.vstx │ ├── testVORBIS.ogg │ ├── testVORCalcTemplate.vor │ ├── testVORDrawTemplate.vor │ ├── testVORImpressTemplate.vor │ ├── testVORWriterTemplate.vor │ ├── testVideoMp4.mp4 │ ├── testWAR.war │ ├── testWAV.wav │ ├── testWEBARCHIVE.webarchive │ ├── testWEBM.webm │ ├── testWEBP.webp │ ├── testWINMAIL.dat │ ├── testWMA.wma │ ├── testWMF.wmf │ ├── testWMF_charset.wmf │ ├── testWMV.wmv │ ├── testWORD.doc │ ├── testWORD.docx │ ├── testWORD2003.xml │ ├── testWORD6.doc │ ├── testWORD_1img.doc │ ├── testWORD_1img.docx │ ├── testWORD_2003ml.xml │ ├── testWORD_2006ml.doc │ ├── testWORD_2006ml.docx │ ├── testWORD_2006ml.xml │ ├── testWORD_3imgs.doc │ ├── testWORD_3imgs.docx │ ├── testWORD_boldHyperlink.doc │ ├── testWORD_boldHyperlink.docx │ ├── testWORD_bold_character_runs.doc │ ├── testWORD_bold_character_runs.docx │ ├── testWORD_bold_character_runs2.doc │ ├── testWORD_bold_character_runs2.docx │ ├── testWORD_charts.docx │ ├── testWORD_closingSmartQInHyperLink.doc │ ├── testWORD_custom_props.doc │ ├── testWORD_custom_props.docx │ ├── testWORD_diagramData.docx │ ├── testWORD_docSecurity.docx │ ├── testWORD_embedded_pdf.doc │ ├── testWORD_embedded_pdf.docx │ ├── testWORD_embedded_pics.docx │ ├── testWORD_embedded_rtf.doc │ ├── testWORD_embeded.doc │ ├── testWORD_embeded.docx │ ├── testWORD_header_hyperlink.doc │ ├── testWORD_italicsSurroundingHyperlink.doc │ ├── testWORD_macros.doc │ ├── testWORD_macros.docm │ ├── testWORD_missing_ooxml_bean1.docx │ ├── testWORD_missing_text.docx │ ├── testWORD_multi_authors.doc │ ├── testWORD_multi_authors.docx │ ├── testWORD_no_format.doc │ ├── testWORD_no_format.docx │ ├── testWORD_null_style.docx │ ├── testWORD_numbered_list.doc │ ├── testWORD_numbered_list.docx │ ├── testWORD_override_list_numbering.doc │ ├── testWORD_override_list_numbering.docx │ ├── testWORD_phonetic.doc │ ├── testWORD_phonetic.docx │ ├── testWORD_protected_passtika.doc │ ├── testWORD_protected_passtika.docx │ ├── testWORD_sdtInTextBox.docx │ ├── testWORD_signed.docx │ ├── testWORD_specialControlCharacter1415.doc │ ├── testWORD_tabular_symbol.doc │ ├── testWORD_template.docx │ ├── testWORD_template.dotx │ ├── testWORD_text_box.docx │ ├── testWORD_totalTimeOutOfRange.docx │ ├── testWORD_truncated.docx │ ├── testWORD_various.doc │ ├── testWORD_various.docx │ ├── testWORKS.wps │ ├── testWORKS2000.wps │ ├── testWORKSSpreadsheet7.0.xlr │ ├── testWORKSWordProcessor3.0.wps │ ├── testWORKSWordProcessor4.0.wps │ ├── testWebVTT.vtt │ ├── testWebVTT_header.vtt │ ├── testWebVTT_simple.vtt │ ├── testWebp_Alpha_Lossless.webp │ ├── testWebp_Alpha_Lossy.webp │ ├── testWindows-x86-32.exe │ ├── testWindowsMediaMeta.asx │ ├── testWordArt.pptx │ ├── testWordPerfect.wpd │ ├── testWordPerfect_5_0.wp │ ├── testWordPerfect_5_1.wp │ ├── testXDP.xdp │ ├── testXFDF.xfdf │ ├── testXHTML.html │ ├── testXLIFF12.xlf │ ├── testXLIFF12.xlz │ ├── testXLSX_Thumbnail.xlsx │ ├── testXML.xml │ ├── testXML2.xml │ ├── testXML3.xml │ ├── testXMP.xmp │ ├── testXPS_various.xps │ ├── testXXE.xml │ ├── testZIP_corrupted_oom.zip │ ├── testZSTD.zstd │ ├── testZ_oom.Z │ ├── testZipEncrypted.zip │ ├── test_TIKA-1251.doc │ ├── test_embedded_zip.pptx │ ├── test_list_override.rtf │ ├── test_mat_text.mat │ ├── test_recursive_embedded.doc │ ├── test_recursive_embedded.docx │ ├── test_recursive_embedded_npe.docx │ ├── testiBooks.ibooks │ ├── testsolidworksAssembly2013SP2.SLDASM │ ├── testsolidworksAssembly2014SP0.SLDASM │ ├── testsolidworksDrawing2013SP2.SLDDRW │ ├── testsolidworksDrawing2014SP0.SLDDRW │ ├── testsolidworksPart2013SP2.SLDPRT │ ├── testsolidworksPart2014SP0.SLDPRT │ └── tika434.html │ └── test-properties │ ├── StringsConfig-full.properties │ ├── StringsConfig-partial.properties │ ├── TesseractOCRConfig-full.properties │ └── TesseractOCRConfig-partial.properties ├── tika-serialization ├── pom.xml └── src │ ├── main │ └── java │ │ └── org │ │ └── apache │ │ └── tika │ │ └── metadata │ │ └── serialization │ │ ├── JsonMetadata.java │ │ ├── JsonMetadataBase.java │ │ ├── JsonMetadataDeserializer.java │ │ ├── JsonMetadataList.java │ │ ├── JsonMetadataSerializer.java │ │ ├── JsonStreamingSerializer.java │ │ └── PrettyMetadataKeyComparator.java │ └── test │ └── java │ └── org │ └── apache │ └── tika │ └── metadata │ └── serialization │ ├── JsonMetadataListTest.java │ └── JsonMetadataTest.java ├── tika-server ├── README.md ├── assembly.xml ├── bin │ ├── init.d │ │ └── tika │ ├── install_tika_service.sh │ ├── tika │ └── tika.in.sh ├── pom.xml └── src │ ├── main │ ├── java │ │ └── org │ │ │ └── apache │ │ │ └── tika │ │ │ └── server │ │ │ ├── DefaultInputStreamFactory.java │ │ │ ├── HTMLHelper.java │ │ │ ├── InputStreamFactory.java │ │ │ ├── MetadataList.java │ │ │ ├── ServerStatus.java │ │ │ ├── ServerStatusWatcher.java │ │ │ ├── ServerTimeouts.java │ │ │ ├── TaskStatus.java │ │ │ ├── TikaLoggingFilter.java │ │ │ ├── TikaServerCli.java │ │ │ ├── TikaServerParseException.java │ │ │ ├── TikaServerParseExceptionMapper.java │ │ │ ├── TikaServerWatchDog.java │ │ │ ├── URLEnabledInputStreamFactory.java │ │ │ ├── resource │ │ │ ├── DetectorResource.java │ │ │ ├── LanguageResource.java │ │ │ ├── MetadataResource.java │ │ │ ├── RecursiveMetadataResource.java │ │ │ ├── TikaDetectors.java │ │ │ ├── TikaMimeTypes.java │ │ │ ├── TikaParsers.java │ │ │ ├── TikaResource.java │ │ │ ├── TikaVersion.java │ │ │ ├── TikaWelcome.java │ │ │ ├── TranslateResource.java │ │ │ └── UnpackerResource.java │ │ │ └── writer │ │ │ ├── CSVMessageBodyWriter.java │ │ │ ├── JSONMessageBodyWriter.java │ │ │ ├── MetadataListMessageBodyWriter.java │ │ │ ├── TarWriter.java │ │ │ ├── TextMessageBodyWriter.java │ │ │ ├── XMPMessageBodyWriter.java │ │ │ └── ZipWriter.java │ └── resources │ │ ├── log4j.properties │ │ ├── tikaserver-template.html │ │ └── tikaserver-version.properties │ └── test │ ├── java │ └── org │ │ └── apache │ │ └── tika │ │ └── server │ │ ├── CXFTestBase.java │ │ ├── DetectorResourceTest.java │ │ ├── LanguageResourceTest.java │ │ ├── MetadataResourceTest.java │ │ ├── NullWebClientLogger.java │ │ ├── RecursiveMetadataResourceTest.java │ │ ├── ServerStatusTest.java │ │ ├── StackTraceOffTest.java │ │ ├── StackTraceTest.java │ │ ├── TikaDetectorsTest.java │ │ ├── TikaMimeTypesTest.java │ │ ├── TikaParsersTest.java │ │ ├── TikaResourceTest.java │ │ ├── TikaServerIntegrationTest.java │ │ ├── TikaVersionTest.java │ │ ├── TikaWelcomeTest.java │ │ ├── TranslateResourceTest.java │ │ └── UnpackerResourceTest.java │ └── resources │ ├── 2exe.docx │ ├── 2pic.doc │ ├── 2pic.docx │ ├── CDEC_WEATHER_2010_03_02 │ ├── Doc1_ole.doc │ ├── english.txt │ ├── foo.csv │ ├── french.txt │ ├── log4j.properties │ ├── logging │ └── log4j_child.xml │ ├── mock │ ├── fake_oom.xml │ ├── heavy_hang_100.xml │ ├── heavy_hang_30000.xml │ ├── null_pointer.xml │ ├── real_oom.xml │ ├── system_exit.xml │ ├── testStaticStdOutErr.xml │ ├── testStdOutErr.xml │ └── thread_interrupt.xml │ ├── org │ └── apache │ │ └── tika │ │ └── server │ │ └── tika-config-for-server-tests.xml │ ├── password.xls │ ├── pic.xls │ ├── pic.xlsx │ ├── test.doc │ ├── testDigilite.fdf │ ├── testHTML.html │ ├── testOCR.pdf │ ├── testPDFTwoTextBoxes.pdf │ ├── testPassword4Spaces.pdf │ ├── testRTF_npeFromWMFInTikaServer.rtf │ ├── testUnicodePassword.pdf │ └── test_recursive_embedded.docx ├── tika-translate ├── pom.xml └── src │ ├── main │ ├── java │ │ └── org │ │ │ └── apache │ │ │ └── tika │ │ │ └── language │ │ │ └── translate │ │ │ ├── AbstractTranslator.java │ │ │ ├── CachedTranslator.java │ │ │ ├── ExternalTranslator.java │ │ │ ├── GoogleTranslator.java │ │ │ ├── JoshuaNetworkTranslator.java │ │ │ ├── Lingo24Translator.java │ │ │ ├── MicrosoftTranslator.java │ │ │ ├── MosesTranslator.java │ │ │ └── YandexTranslator.java │ └── resources │ │ ├── META-INF │ │ └── services │ │ │ └── org.apache.tika.language.translate.Translator │ │ └── org │ │ └── apache │ │ └── tika │ │ └── language │ │ └── translate │ │ ├── translator.google.properties │ │ ├── translator.joshua.properties │ │ ├── translator.lingo24.properties │ │ ├── translator.microsoft.properties │ │ ├── translator.moses.properties │ │ └── translator.yandex.properties │ └── test │ └── java │ └── org │ └── apache │ └── tika │ └── language │ └── translate │ ├── CachedTranslatorTest.java │ ├── GoogleTranslatorTest.java │ ├── JoshuaNetworkTranslatorTest.java │ ├── Lingo24TranslatorTest.java │ ├── MicrosoftTranslatorTest.java │ ├── MosesTranslatorTest.java │ └── YandexTranslatorTest.java └── tika-xmp ├── pom.xml └── src ├── main └── java │ └── org │ └── apache │ └── tika │ └── xmp │ ├── XMPMetadata.java │ └── convert │ ├── AbstractConverter.java │ ├── GenericConverter.java │ ├── ITikaToXMPConverter.java │ ├── MSOfficeBinaryConverter.java │ ├── MSOfficeXMLConverter.java │ ├── Namespace.java │ ├── OpenDocumentConverter.java │ ├── RTFConverter.java │ └── TikaToXMP.java └── test └── java └── org └── apache └── tika └── xmp ├── TikaToXMPTest.java └── XMPMetadataTest.java /.gitattributes: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/.gitattributes -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/.gitignore -------------------------------------------------------------------------------- /CHANGES.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/CHANGES.txt -------------------------------------------------------------------------------- /HEADER.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/HEADER.txt -------------------------------------------------------------------------------- /KEYS: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/KEYS -------------------------------------------------------------------------------- /LICENSE.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/LICENSE.txt -------------------------------------------------------------------------------- /NOTICE.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/NOTICE.txt -------------------------------------------------------------------------------- /README-apache.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/README-apache.md -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/README.md -------------------------------------------------------------------------------- /assembly.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/assembly.xml -------------------------------------------------------------------------------- /pom.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/pom.xml -------------------------------------------------------------------------------- /tika-app/pom.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-app/pom.xml -------------------------------------------------------------------------------- /tika-app/src/main/appended-resources/META-INF/LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-app/src/main/appended-resources/META-INF/LICENSE -------------------------------------------------------------------------------- /tika-app/src/main/assembly/standalone.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-app/src/main/assembly/standalone.xml -------------------------------------------------------------------------------- /tika-app/src/main/java/org/apache/tika/cli/TikaCLI.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-app/src/main/java/org/apache/tika/cli/TikaCLI.java -------------------------------------------------------------------------------- /tika-app/src/main/java/org/apache/tika/gui/TikaGUI.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-app/src/main/java/org/apache/tika/gui/TikaGUI.java -------------------------------------------------------------------------------- /tika-app/src/main/resources/log4j.properties: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-app/src/main/resources/log4j.properties -------------------------------------------------------------------------------- /tika-app/src/main/resources/log4j_batch_process.properties: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-app/src/main/resources/log4j_batch_process.properties -------------------------------------------------------------------------------- /tika-app/src/main/resources/org/apache/tika/gui/tika.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-app/src/main/resources/org/apache/tika/gui/tika.png -------------------------------------------------------------------------------- /tika-app/src/main/resources/tika-app-batch-config.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-app/src/main/resources/tika-app-batch-config.xml -------------------------------------------------------------------------------- /tika-app/src/test/java/org/apache/tika/cli/TikaCLITest.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-app/src/test/java/org/apache/tika/cli/TikaCLITest.java -------------------------------------------------------------------------------- /tika-app/src/test/resources/log4j_batch_process_test.properties: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-app/src/test/resources/log4j_batch_process_test.properties -------------------------------------------------------------------------------- /tika-app/src/test/resources/test-data/alice.cli.test: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-app/src/test/resources/test-data/alice.cli.test -------------------------------------------------------------------------------- /tika-app/src/test/resources/test-data/bad_xml.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-app/src/test/resources/test-data/bad_xml.xml -------------------------------------------------------------------------------- /tika-app/src/test/resources/test-data/coffee.xls: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-app/src/test/resources/test-data/coffee.xls -------------------------------------------------------------------------------- /tika-app/src/test/resources/test-data/test-documents.tgz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-app/src/test/resources/test-data/test-documents.tgz -------------------------------------------------------------------------------- /tika-app/src/test/resources/test-data/testJsonMultipleInts.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-app/src/test/resources/test-data/testJsonMultipleInts.html -------------------------------------------------------------------------------- /tika-app/src/test/resources/test-data/testMultipleSheets.numbers: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-app/src/test/resources/test-data/testMultipleSheets.numbers -------------------------------------------------------------------------------- /tika-app/src/test/resources/test-data/testWithSubdirs.zip: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-app/src/test/resources/test-data/testWithSubdirs.zip -------------------------------------------------------------------------------- /tika-app/src/test/resources/test-data/testZip_absolutePath.zip: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-app/src/test/resources/test-data/testZip_absolutePath.zip -------------------------------------------------------------------------------- /tika-app/src/test/resources/test-data/testZip_relative.zip: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-app/src/test/resources/test-data/testZip_relative.zip -------------------------------------------------------------------------------- /tika-app/src/test/resources/test-data/testZip_zeroByte.zip: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-app/src/test/resources/test-data/testZip_zeroByte.zip -------------------------------------------------------------------------------- /tika-app/src/test/resources/test-data/tika-config1.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-app/src/test/resources/test-data/tika-config1.xml -------------------------------------------------------------------------------- /tika-app/src/test/resources/test-data/tika-config2.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-app/src/test/resources/test-data/tika-config2.xml -------------------------------------------------------------------------------- /tika-app/src/test/resources/test-data/welsh_corpus.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-app/src/test/resources/test-data/welsh_corpus.txt -------------------------------------------------------------------------------- /tika-batch/pom.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-batch/pom.xml -------------------------------------------------------------------------------- /tika-batch/src/main/java/org/apache/tika/batch/BatchProcess.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-batch/src/main/java/org/apache/tika/batch/BatchProcess.java -------------------------------------------------------------------------------- /tika-batch/src/main/java/org/apache/tika/batch/FileResource.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-batch/src/main/java/org/apache/tika/batch/FileResource.java -------------------------------------------------------------------------------- /tika-batch/src/main/java/org/apache/tika/batch/FileStarted.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-batch/src/main/java/org/apache/tika/batch/FileStarted.java -------------------------------------------------------------------------------- /tika-batch/src/main/java/org/apache/tika/batch/Interrupter.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-batch/src/main/java/org/apache/tika/batch/Interrupter.java -------------------------------------------------------------------------------- /tika-batch/src/main/java/org/apache/tika/batch/ParserFactory.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-batch/src/main/java/org/apache/tika/batch/ParserFactory.java -------------------------------------------------------------------------------- /tika-batch/src/main/java/org/apache/tika/batch/fs/FSUtil.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-batch/src/main/java/org/apache/tika/batch/fs/FSUtil.java -------------------------------------------------------------------------------- /tika-batch/src/main/java/org/apache/tika/util/PropsUtil.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-batch/src/main/java/org/apache/tika/util/PropsUtil.java -------------------------------------------------------------------------------- /tika-batch/src/main/java/org/apache/tika/util/XMLDOMUtil.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-batch/src/main/java/org/apache/tika/util/XMLDOMUtil.java -------------------------------------------------------------------------------- /tika-batch/src/main/java/overview.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-batch/src/main/java/overview.html -------------------------------------------------------------------------------- /tika-batch/src/test/java/org/apache/tika/batch/fs/FSUtilTest.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-batch/src/test/java/org/apache/tika/batch/fs/FSUtilTest.java -------------------------------------------------------------------------------- /tika-batch/src/test/resources/log4j-on.properties: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-batch/src/test/resources/log4j-on.properties -------------------------------------------------------------------------------- /tika-batch/src/test/resources/log4j.properties: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-batch/src/test/resources/log4j.properties -------------------------------------------------------------------------------- /tika-batch/src/test/resources/log4j_process.properties: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-batch/src/test/resources/log4j_process.properties -------------------------------------------------------------------------------- /tika-batch/src/test/resources/test-documents/null_pointer.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-batch/src/test/resources/test-documents/null_pointer.xml -------------------------------------------------------------------------------- /tika-batch/src/test/resources/test-input/basic/test0.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-batch/src/test/resources/test-input/basic/test0.xml -------------------------------------------------------------------------------- /tika-batch/src/test/resources/test-input/hierarchical/test1.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-batch/src/test/resources/test-input/hierarchical/test1.xml -------------------------------------------------------------------------------- /tika-batch/src/test/resources/test-input/no_restart/test1_ok.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-batch/src/test/resources/test-input/no_restart/test1_ok.xml -------------------------------------------------------------------------------- /tika-batch/src/test/resources/test-input/no_restart/test3_ok.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-batch/src/test/resources/test-input/no_restart/test3_ok.xml -------------------------------------------------------------------------------- /tika-batch/src/test/resources/test-input/noisy_parsers/test0.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-batch/src/test/resources/test-input/noisy_parsers/test0.xml -------------------------------------------------------------------------------- /tika-batch/src/test/resources/test-input/oom/test0_sleep.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-batch/src/test/resources/test-input/oom/test0_sleep.xml -------------------------------------------------------------------------------- /tika-batch/src/test/resources/test-input/oom/test1_heavy_hang.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-batch/src/test/resources/test-input/oom/test1_heavy_hang.xml -------------------------------------------------------------------------------- /tika-batch/src/test/resources/test-input/oom/test2_ok.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-batch/src/test/resources/test-input/oom/test2_ok.xml -------------------------------------------------------------------------------- /tika-batch/src/test/resources/test-input/oom/test3_oom.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-batch/src/test/resources/test-input/oom/test3_oom.xml -------------------------------------------------------------------------------- /tika-batch/src/test/resources/test-input/oom/test4_ok.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-batch/src/test/resources/test-input/oom/test4_ok.xml -------------------------------------------------------------------------------- /tika-batch/src/test/resources/test-input/oom/test5_ok.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-batch/src/test/resources/test-input/oom/test5_ok.xml -------------------------------------------------------------------------------- /tika-batch/src/test/resources/test-input/system_exit/test3_ok.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-batch/src/test/resources/test-input/system_exit/test3_ok.xml -------------------------------------------------------------------------------- /tika-batch/src/test/resources/test-input/system_exit/test4_ok.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-batch/src/test/resources/test-input/system_exit/test4_ok.xml -------------------------------------------------------------------------------- /tika-batch/src/test/resources/test-input/system_exit/test5_ok.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-batch/src/test/resources/test-input/system_exit/test5_ok.xml -------------------------------------------------------------------------------- /tika-batch/src/test/resources/testFileList.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-batch/src/test/resources/testFileList.txt -------------------------------------------------------------------------------- /tika-batch/src/test/resources/tika-batch-config-broken.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-batch/src/test/resources/tika-batch-config-broken.xml -------------------------------------------------------------------------------- /tika-batch/src/test/resources/tika-batch-config-test.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-batch/src/test/resources/tika-batch-config-test.xml -------------------------------------------------------------------------------- /tika-bundle/pom.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-bundle/pom.xml -------------------------------------------------------------------------------- /tika-bundle/src/main/appended-resources/META-INF/LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-bundle/src/main/appended-resources/META-INF/LICENSE -------------------------------------------------------------------------------- /tika-bundle/src/main/resources/META-INF/MANIFEST.MF: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-bundle/src/main/resources/META-INF/MANIFEST.MF -------------------------------------------------------------------------------- /tika-bundle/src/test/java/org/apache/tika/bundle/BundleIT.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-bundle/src/test/java/org/apache/tika/bundle/BundleIT.java -------------------------------------------------------------------------------- /tika-bundle/src/test/resources/log4j.properties: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-bundle/src/test/resources/log4j.properties -------------------------------------------------------------------------------- /tika-bundle/src/test/resources/test-documents.zip: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-bundle/src/test/resources/test-documents.zip -------------------------------------------------------------------------------- /tika-bundle/src/test/resources/testOCR.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-bundle/src/test/resources/testOCR.jpg -------------------------------------------------------------------------------- /tika-bundle/test-bundles.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-bundle/test-bundles.xml -------------------------------------------------------------------------------- /tika-core/pom.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/pom.xml -------------------------------------------------------------------------------- /tika-core/src/main/appended-resources/META-INF/LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/appended-resources/META-INF/LICENSE -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/Tika.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/Tika.java -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/config/Field.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/config/Field.java -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/config/Initializable.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/config/Initializable.java -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/config/Param.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/config/Param.java -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/config/ParamField.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/config/ParamField.java -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/config/ServiceLoader.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/config/ServiceLoader.java -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/config/TikaActivator.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/config/TikaActivator.java -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/config/TikaConfig.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/config/TikaConfig.java -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/config/package-info.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/config/package-info.java -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/detect/Detector.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/detect/Detector.java -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/detect/EmptyDetector.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/detect/EmptyDetector.java -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/detect/MagicDetector.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/detect/MagicDetector.java -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/detect/NameDetector.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/detect/NameDetector.java -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/detect/TextDetector.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/detect/TextDetector.java -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/detect/TrainedModel.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/detect/TrainedModel.java -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/detect/TypeDetector.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/detect/TypeDetector.java -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/detect/package-info.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/detect/package-info.java -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/embedder/Embedder.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/embedder/Embedder.java -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/fork/ForkClient.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/fork/ForkClient.java -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/fork/ForkParser.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/fork/ForkParser.java -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/fork/ForkProxy.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/fork/ForkProxy.java -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/fork/ForkResource.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/fork/ForkResource.java -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/fork/ForkServer.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/fork/ForkServer.java -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/fork/TimeoutLimits.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/fork/TimeoutLimits.java -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/fork/package-info.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/fork/package-info.java -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/io/ClosedInputStream.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/io/ClosedInputStream.java -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/io/EndianUtils.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/io/EndianUtils.java -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/io/FilenameUtils.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/io/FilenameUtils.java -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/io/IOUtils.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/io/IOUtils.java -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/io/NullInputStream.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/io/NullInputStream.java -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/io/NullOutputStream.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/io/NullOutputStream.java -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/io/ProxyInputStream.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/io/ProxyInputStream.java -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/io/TaggedIOException.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/io/TaggedIOException.java -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/io/TaggedInputStream.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/io/TaggedInputStream.java -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/io/TailStream.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/io/TailStream.java -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/io/TikaInputStream.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/io/TikaInputStream.java -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/io/package-info.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/io/package-info.java -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/metadata/Database.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/metadata/Database.java -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/metadata/DublinCore.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/metadata/DublinCore.java -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/metadata/Font.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/metadata/Font.java -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/metadata/Geographic.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/metadata/Geographic.java -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/metadata/HTML.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/metadata/HTML.java -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/metadata/HttpHeaders.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/metadata/HttpHeaders.java -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/metadata/IPTC.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/metadata/IPTC.java -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/metadata/MSOffice.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/metadata/MSOffice.java -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/metadata/Message.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/metadata/Message.java -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/metadata/Metadata.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/metadata/Metadata.java -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/metadata/Office.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/metadata/Office.java -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/metadata/PDF.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/metadata/PDF.java -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/metadata/PagedText.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/metadata/PagedText.java -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/metadata/Photoshop.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/metadata/Photoshop.java -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/metadata/Property.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/metadata/Property.java -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/metadata/QuattroPro.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/metadata/QuattroPro.java -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/metadata/RTFMetadata.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/metadata/RTFMetadata.java -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/metadata/TIFF.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/metadata/TIFF.java -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/metadata/WordPerfect.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/metadata/WordPerfect.java -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/metadata/XMP.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/metadata/XMP.java -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/metadata/XMPDM.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/metadata/XMPDM.java -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/metadata/XMPIdq.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/metadata/XMPIdq.java -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/metadata/XMPMM.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/metadata/XMPMM.java -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/metadata/XMPRights.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/metadata/XMPRights.java -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/mime/AndClause.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/mime/AndClause.java -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/mime/Clause.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/mime/Clause.java -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/mime/HexCoDec.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/mime/HexCoDec.java -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/mime/Magic.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/mime/Magic.java -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/mime/MagicMatch.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/mime/MagicMatch.java -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/mime/MediaType.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/mime/MediaType.java -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/mime/MimeType.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/mime/MimeType.java -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/mime/MimeTypes.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/mime/MimeTypes.java -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/mime/MimeTypesReader.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/mime/MimeTypesReader.java -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/mime/OrClause.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/mime/OrClause.java -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/mime/Patterns.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/mime/Patterns.java -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/mime/package-info.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/mime/package-info.java -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/package-info.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/package-info.java -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/parser/CryptoParser.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/parser/CryptoParser.java -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/parser/DefaultParser.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/parser/DefaultParser.java -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/parser/EmptyParser.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/parser/EmptyParser.java -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/parser/ErrorParser.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/parser/ErrorParser.java -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/parser/NetworkParser.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/parser/NetworkParser.java -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/parser/ParseContext.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/parser/ParseContext.java -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/parser/Parser.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/parser/Parser.java -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/parser/ParserFactory.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/parser/ParserFactory.java -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/parser/ParsingReader.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/parser/ParsingReader.java -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/parser/package-info.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/parser/package-info.java -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/sax/CleanPhoneText.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/sax/CleanPhoneText.java -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/sax/Link.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/sax/Link.java -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/sax/LinkBuilder.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/sax/LinkBuilder.java -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/sax/StandardsText.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/sax/StandardsText.java -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/sax/package-info.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/sax/package-info.java -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/sax/xpath/Matcher.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/sax/xpath/Matcher.java -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/utils/CharsetUtils.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/utils/CharsetUtils.java -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/utils/DateUtils.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/utils/DateUtils.java -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/utils/ExceptionUtils.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/utils/ExceptionUtils.java -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/utils/ParserUtils.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/utils/ParserUtils.java -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/utils/ProcessUtils.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/utils/ProcessUtils.java -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/utils/RegexUtils.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/utils/RegexUtils.java -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/utils/SystemUtils.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/utils/SystemUtils.java -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/utils/XMLReaderUtils.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/utils/XMLReaderUtils.java -------------------------------------------------------------------------------- /tika-core/src/main/java/org/apache/tika/utils/package-info.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/java/org/apache/tika/utils/package-info.java -------------------------------------------------------------------------------- /tika-core/src/main/resources/org/apache/tika/language/be.ngp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/resources/org/apache/tika/language/be.ngp -------------------------------------------------------------------------------- /tika-core/src/main/resources/org/apache/tika/language/ca.ngp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/resources/org/apache/tika/language/ca.ngp -------------------------------------------------------------------------------- /tika-core/src/main/resources/org/apache/tika/language/da.ngp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/resources/org/apache/tika/language/da.ngp -------------------------------------------------------------------------------- /tika-core/src/main/resources/org/apache/tika/language/de.ngp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/resources/org/apache/tika/language/de.ngp -------------------------------------------------------------------------------- /tika-core/src/main/resources/org/apache/tika/language/el.ngp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/resources/org/apache/tika/language/el.ngp -------------------------------------------------------------------------------- /tika-core/src/main/resources/org/apache/tika/language/en.ngp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/resources/org/apache/tika/language/en.ngp -------------------------------------------------------------------------------- /tika-core/src/main/resources/org/apache/tika/language/eo.ngp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/resources/org/apache/tika/language/eo.ngp -------------------------------------------------------------------------------- /tika-core/src/main/resources/org/apache/tika/language/es.ngp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/resources/org/apache/tika/language/es.ngp -------------------------------------------------------------------------------- /tika-core/src/main/resources/org/apache/tika/language/et.ngp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/resources/org/apache/tika/language/et.ngp -------------------------------------------------------------------------------- /tika-core/src/main/resources/org/apache/tika/language/fa.ngp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/resources/org/apache/tika/language/fa.ngp -------------------------------------------------------------------------------- /tika-core/src/main/resources/org/apache/tika/language/fi.ngp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/resources/org/apache/tika/language/fi.ngp -------------------------------------------------------------------------------- /tika-core/src/main/resources/org/apache/tika/language/fr.ngp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/resources/org/apache/tika/language/fr.ngp -------------------------------------------------------------------------------- /tika-core/src/main/resources/org/apache/tika/language/gl.ngp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/resources/org/apache/tika/language/gl.ngp -------------------------------------------------------------------------------- /tika-core/src/main/resources/org/apache/tika/language/hu.ngp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/resources/org/apache/tika/language/hu.ngp -------------------------------------------------------------------------------- /tika-core/src/main/resources/org/apache/tika/language/is.ngp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/resources/org/apache/tika/language/is.ngp -------------------------------------------------------------------------------- /tika-core/src/main/resources/org/apache/tika/language/it.ngp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/resources/org/apache/tika/language/it.ngp -------------------------------------------------------------------------------- /tika-core/src/main/resources/org/apache/tika/language/lt.ngp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/resources/org/apache/tika/language/lt.ngp -------------------------------------------------------------------------------- /tika-core/src/main/resources/org/apache/tika/language/nl.ngp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/resources/org/apache/tika/language/nl.ngp -------------------------------------------------------------------------------- /tika-core/src/main/resources/org/apache/tika/language/no.ngp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/resources/org/apache/tika/language/no.ngp -------------------------------------------------------------------------------- /tika-core/src/main/resources/org/apache/tika/language/pl.ngp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/resources/org/apache/tika/language/pl.ngp -------------------------------------------------------------------------------- /tika-core/src/main/resources/org/apache/tika/language/pt.ngp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/resources/org/apache/tika/language/pt.ngp -------------------------------------------------------------------------------- /tika-core/src/main/resources/org/apache/tika/language/ro.ngp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/resources/org/apache/tika/language/ro.ngp -------------------------------------------------------------------------------- /tika-core/src/main/resources/org/apache/tika/language/ru.ngp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/resources/org/apache/tika/language/ru.ngp -------------------------------------------------------------------------------- /tika-core/src/main/resources/org/apache/tika/language/sk.ngp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/resources/org/apache/tika/language/sk.ngp -------------------------------------------------------------------------------- /tika-core/src/main/resources/org/apache/tika/language/sl.ngp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/resources/org/apache/tika/language/sl.ngp -------------------------------------------------------------------------------- /tika-core/src/main/resources/org/apache/tika/language/sv.ngp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/resources/org/apache/tika/language/sv.ngp -------------------------------------------------------------------------------- /tika-core/src/main/resources/org/apache/tika/language/th.ngp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/resources/org/apache/tika/language/th.ngp -------------------------------------------------------------------------------- /tika-core/src/main/resources/org/apache/tika/language/uk.ngp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/main/resources/org/apache/tika/language/uk.ngp -------------------------------------------------------------------------------- /tika-core/src/test/java/org/apache/tika/TikaDetectionTest.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/test/java/org/apache/tika/TikaDetectionTest.java -------------------------------------------------------------------------------- /tika-core/src/test/java/org/apache/tika/TikaIT.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/test/java/org/apache/tika/TikaIT.java -------------------------------------------------------------------------------- /tika-core/src/test/java/org/apache/tika/TikaTest.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/test/java/org/apache/tika/TikaTest.java -------------------------------------------------------------------------------- /tika-core/src/test/java/org/apache/tika/config/DummyExecutor.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/test/java/org/apache/tika/config/DummyExecutor.java -------------------------------------------------------------------------------- /tika-core/src/test/java/org/apache/tika/config/DummyParser.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/test/java/org/apache/tika/config/DummyParser.java -------------------------------------------------------------------------------- /tika-core/src/test/java/org/apache/tika/config/ParamTest.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/test/java/org/apache/tika/config/ParamTest.java -------------------------------------------------------------------------------- /tika-core/src/test/java/org/apache/tika/fork/ForkParserTest.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/test/java/org/apache/tika/fork/ForkParserTest.java -------------------------------------------------------------------------------- /tika-core/src/test/java/org/apache/tika/fork/ForkTestParser.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/test/java/org/apache/tika/fork/ForkTestParser.java -------------------------------------------------------------------------------- /tika-core/src/test/java/org/apache/tika/io/EndianUtilsTest.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/test/java/org/apache/tika/io/EndianUtilsTest.java -------------------------------------------------------------------------------- /tika-core/src/test/java/org/apache/tika/io/FilenameUtilsTest.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/test/java/org/apache/tika/io/FilenameUtilsTest.java -------------------------------------------------------------------------------- /tika-core/src/test/java/org/apache/tika/io/TailStreamTest.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/test/java/org/apache/tika/io/TailStreamTest.java -------------------------------------------------------------------------------- /tika-core/src/test/java/org/apache/tika/mime/MediaTypeTest.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/test/java/org/apache/tika/mime/MediaTypeTest.java -------------------------------------------------------------------------------- /tika-core/src/test/java/org/apache/tika/mime/PatternsTest.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/test/java/org/apache/tika/mime/PatternsTest.java -------------------------------------------------------------------------------- /tika-core/src/test/java/org/apache/tika/parser/DummyParser.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/test/java/org/apache/tika/parser/DummyParser.java -------------------------------------------------------------------------------- /tika-core/src/test/java/org/apache/tika/sax/SerializerTest.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/test/java/org/apache/tika/sax/SerializerTest.java -------------------------------------------------------------------------------- /tika-core/src/test/java/org/apache/tika/utils/RegexUtilsTest.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/test/java/org/apache/tika/utils/RegexUtilsTest.java -------------------------------------------------------------------------------- /tika-core/src/test/resources/log4j.properties: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/test/resources/log4j.properties -------------------------------------------------------------------------------- /tika-core/src/test/resources/org/apache/tika/io/test.txt: -------------------------------------------------------------------------------- 1 | Hello, World! -------------------------------------------------------------------------------- /tika-core/src/test/resources/org/apache/tika/language/da.test: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/test/resources/org/apache/tika/language/da.test -------------------------------------------------------------------------------- /tika-core/src/test/resources/org/apache/tika/language/de.test: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/test/resources/org/apache/tika/language/de.test -------------------------------------------------------------------------------- /tika-core/src/test/resources/org/apache/tika/language/el.test: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/test/resources/org/apache/tika/language/el.test -------------------------------------------------------------------------------- /tika-core/src/test/resources/org/apache/tika/language/en.test: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/test/resources/org/apache/tika/language/en.test -------------------------------------------------------------------------------- /tika-core/src/test/resources/org/apache/tika/language/es.test: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/test/resources/org/apache/tika/language/es.test -------------------------------------------------------------------------------- /tika-core/src/test/resources/org/apache/tika/language/et.test: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/test/resources/org/apache/tika/language/et.test -------------------------------------------------------------------------------- /tika-core/src/test/resources/org/apache/tika/language/fi.test: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/test/resources/org/apache/tika/language/fi.test -------------------------------------------------------------------------------- /tika-core/src/test/resources/org/apache/tika/language/fr.test: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/test/resources/org/apache/tika/language/fr.test -------------------------------------------------------------------------------- /tika-core/src/test/resources/org/apache/tika/language/it.test: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/test/resources/org/apache/tika/language/it.test -------------------------------------------------------------------------------- /tika-core/src/test/resources/org/apache/tika/language/lt.test: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/test/resources/org/apache/tika/language/lt.test -------------------------------------------------------------------------------- /tika-core/src/test/resources/org/apache/tika/language/nl.test: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/test/resources/org/apache/tika/language/nl.test -------------------------------------------------------------------------------- /tika-core/src/test/resources/org/apache/tika/language/pt.test: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/test/resources/org/apache/tika/language/pt.test -------------------------------------------------------------------------------- /tika-core/src/test/resources/org/apache/tika/language/sv.test: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/test/resources/org/apache/tika/language/sv.test -------------------------------------------------------------------------------- /tika-core/src/test/resources/org/apache/tika/mime/circles.svg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/test/resources/org/apache/tika/mime/circles.svg -------------------------------------------------------------------------------- /tika-core/src/test/resources/org/apache/tika/mime/datamatrix.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/test/resources/org/apache/tika/mime/datamatrix.png -------------------------------------------------------------------------------- /tika-core/src/test/resources/org/apache/tika/mime/htmlfragment: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/test/resources/org/apache/tika/mime/htmlfragment -------------------------------------------------------------------------------- /tika-core/src/test/resources/org/apache/tika/mime/stylesheet.xsl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/test/resources/org/apache/tika/mime/stylesheet.xsl -------------------------------------------------------------------------------- /tika-core/src/test/resources/org/apache/tika/mime/test-iso-8859-1.xml: -------------------------------------------------------------------------------- 1 | 2 | -------------------------------------------------------------------------------- /tika-core/src/test/resources/org/apache/tika/mime/test-utf8-bom.xml: -------------------------------------------------------------------------------- 1 | 2 | -------------------------------------------------------------------------------- /tika-core/src/test/resources/org/apache/tika/mime/test-utf8.xml: -------------------------------------------------------------------------------- 1 | 2 | -------------------------------------------------------------------------------- /tika-core/src/test/resources/org/apache/tika/mime/test.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/test/resources/org/apache/tika/mime/test.html -------------------------------------------------------------------------------- /tika-core/src/test/resources/org/apache/tika/mime/test.xls: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/test/resources/org/apache/tika/mime/test.xls -------------------------------------------------------------------------------- /tika-core/src/test/resources/test-documents/basic_embedded.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/test/resources/test-documents/basic_embedded.xml -------------------------------------------------------------------------------- /tika-core/src/test/resources/test-documents/embedded_then_npe.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/test/resources/test-documents/embedded_then_npe.xml -------------------------------------------------------------------------------- /tika-core/src/test/resources/test-documents/embedded_with_npe.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/test/resources/test-documents/embedded_with_npe.xml -------------------------------------------------------------------------------- /tika-core/src/test/resources/test-documents/example.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-core/src/test/resources/test-documents/example.xml -------------------------------------------------------------------------------- /tika-deployment/tika-snap-app/snapcraft.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-deployment/tika-snap-app/snapcraft.yaml -------------------------------------------------------------------------------- /tika-deployment/tika-snap-server/snapcraft.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-deployment/tika-snap-server/snapcraft.yaml -------------------------------------------------------------------------------- /tika-dl/pom.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-dl/pom.xml -------------------------------------------------------------------------------- /tika-dl/src/test/resources/org/apache/tika/dl/imagerec/cat.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-dl/src/test/resources/org/apache/tika/dl/imagerec/cat.jpg -------------------------------------------------------------------------------- /tika-dl/src/test/resources/org/apache/tika/dl/imagerec/lion.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-dl/src/test/resources/org/apache/tika/dl/imagerec/lion.jpg -------------------------------------------------------------------------------- /tika-dotnet/pom.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-dotnet/pom.xml -------------------------------------------------------------------------------- /tika-dotnet/src/main/java/Tika/Tika.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-dotnet/src/main/java/Tika/Tika.java -------------------------------------------------------------------------------- /tika-eval/.gitignore: -------------------------------------------------------------------------------- 1 | !model_20190626.bin -------------------------------------------------------------------------------- /tika-eval/pom.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/pom.xml -------------------------------------------------------------------------------- /tika-eval/src/main/java/org/apache/tika/eval/EvalFilePaths.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/java/org/apache/tika/eval/EvalFilePaths.java -------------------------------------------------------------------------------- /tika-eval/src/main/java/org/apache/tika/eval/ExtractComparer.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/java/org/apache/tika/eval/ExtractComparer.java -------------------------------------------------------------------------------- /tika-eval/src/main/java/org/apache/tika/eval/ExtractProfiler.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/java/org/apache/tika/eval/ExtractProfiler.java -------------------------------------------------------------------------------- /tika-eval/src/main/java/org/apache/tika/eval/TikaEvalCLI.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/java/org/apache/tika/eval/TikaEvalCLI.java -------------------------------------------------------------------------------- /tika-eval/src/main/java/org/apache/tika/eval/db/ColInfo.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/java/org/apache/tika/eval/db/ColInfo.java -------------------------------------------------------------------------------- /tika-eval/src/main/java/org/apache/tika/eval/db/Cols.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/java/org/apache/tika/eval/db/Cols.java -------------------------------------------------------------------------------- /tika-eval/src/main/java/org/apache/tika/eval/db/DBBuffer.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/java/org/apache/tika/eval/db/DBBuffer.java -------------------------------------------------------------------------------- /tika-eval/src/main/java/org/apache/tika/eval/db/H2Util.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/java/org/apache/tika/eval/db/H2Util.java -------------------------------------------------------------------------------- /tika-eval/src/main/java/org/apache/tika/eval/db/JDBCUtil.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/java/org/apache/tika/eval/db/JDBCUtil.java -------------------------------------------------------------------------------- /tika-eval/src/main/java/org/apache/tika/eval/db/MimeBuffer.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/java/org/apache/tika/eval/db/MimeBuffer.java -------------------------------------------------------------------------------- /tika-eval/src/main/java/org/apache/tika/eval/db/TableInfo.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/java/org/apache/tika/eval/db/TableInfo.java -------------------------------------------------------------------------------- /tika-eval/src/main/java/org/apache/tika/eval/io/DBWriter.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/java/org/apache/tika/eval/io/DBWriter.java -------------------------------------------------------------------------------- /tika-eval/src/main/java/org/apache/tika/eval/io/IDBWriter.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/java/org/apache/tika/eval/io/IDBWriter.java -------------------------------------------------------------------------------- /tika-eval/src/main/java/org/apache/tika/eval/io/XMLLogReader.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/java/org/apache/tika/eval/io/XMLLogReader.java -------------------------------------------------------------------------------- /tika-eval/src/main/java/org/apache/tika/eval/langid/Language.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/java/org/apache/tika/eval/langid/Language.java -------------------------------------------------------------------------------- /tika-eval/src/main/java/org/apache/tika/eval/reports/Report.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/java/org/apache/tika/eval/reports/Report.java -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/afr: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/afr -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/amh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/amh -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/ara: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/ara -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/asm: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/asm -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/ast: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/ast -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/aze: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/aze -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/azj: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/azj -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/bak: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/bak -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/ban: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/ban -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/bel: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/bel -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/ben: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/ben -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/bos: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/bos -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/bre: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/bre -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/bul: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/bul -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/cat: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/cat -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/ceb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/ceb -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/ces: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/ces -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/che: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/che -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/ckb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/ckb -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/cmn: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/cmn -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/cym: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/cym -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/dan: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/dan -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/deu: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/deu -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/div: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/div -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/ekk: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/ekk -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/ell: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/ell -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/eng: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/eng -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/epo: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/epo -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/est: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/est -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/eus: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/eus -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/fao: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/fao -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/fas: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/fas -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/fin: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/fin -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/fra: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/fra -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/fry: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/fry -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/gle: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/gle -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/glg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/glg -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/gsw: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/gsw -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/guj: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/guj -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/hat: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/hat -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/heb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/heb -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/hin: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/hin -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/hrv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/hrv -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/hun: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/hun -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/hye: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/hye -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/ind: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/ind -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/isl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/isl -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/ita: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/ita -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/jav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/jav -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/jpn: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/jpn -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/kan: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/kan -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/kat: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/kat -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/kaz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/kaz -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/kin: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/kin -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/kir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/kir -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/kor: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/kor -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/kur: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/kur -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/lat: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/lat -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/lav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/lav -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/lim: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/lim -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/lit: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/lit -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/ltz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/ltz -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/lug: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/lug -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/lvs: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/lvs -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/mal: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/mal -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/mar: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/mar -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/mhr: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/mhr -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/min: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/min -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/mkd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/mkd -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/mlg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/mlg -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/mlt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/mlt -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/mon: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/mon -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/mri: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/mri -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/msa: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/msa -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/nan: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/nan -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/nds: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/nds -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/nep: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/nep -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/nld: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/nld -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/nno: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/nno -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/nob: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/nob -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/oci: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/oci -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/ori: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/ori -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/pan: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/pan -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/pes: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/pes -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/plt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/plt -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/pnb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/pnb -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/pol: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/pol -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/por: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/por -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/pus: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/pus -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/ron: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/ron -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/rus: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/rus -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/san: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/san -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/sin: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/sin -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/slk: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/slk -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/slv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/slv -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/snd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/snd -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/som: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/som -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/spa: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/spa -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/sqi: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/sqi -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/srp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/srp -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/sun: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/sun -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/swa: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/swa -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/swe: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/swe -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/tam: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/tam -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/tat: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/tat -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/tel: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/tel -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/tgk: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/tgk -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/tgl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/tgl -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/tha: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/tha -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/tuk: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/tuk -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/tur: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/tur -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/uig: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/uig -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/ukr: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/ukr -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/urd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/urd -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/uzb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/uzb -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/vie: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/vie -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/vol: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/vol -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/war: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/war -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/xho: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/xho -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/yid: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/yid -------------------------------------------------------------------------------- /tika-eval/src/main/resources/common_tokens/zul: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/common_tokens/zul -------------------------------------------------------------------------------- /tika-eval/src/main/resources/comparison-reports-pg.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/comparison-reports-pg.xml -------------------------------------------------------------------------------- /tika-eval/src/main/resources/comparison-reports.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/comparison-reports.xml -------------------------------------------------------------------------------- /tika-eval/src/main/resources/db.properties: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/db.properties -------------------------------------------------------------------------------- /tika-eval/src/main/resources/log4j.properties: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/log4j.properties -------------------------------------------------------------------------------- /tika-eval/src/main/resources/lucene-analyzers.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/lucene-analyzers.json -------------------------------------------------------------------------------- /tika-eval/src/main/resources/lucene-char-mapping.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/lucene-char-mapping.txt -------------------------------------------------------------------------------- /tika-eval/src/main/resources/opennlp/model_20190626.bin: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/opennlp/model_20190626.bin -------------------------------------------------------------------------------- /tika-eval/src/main/resources/profile-reports.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/profile-reports.xml -------------------------------------------------------------------------------- /tika-eval/src/main/resources/tika-eval-comparison-config.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/tika-eval-comparison-config.xml -------------------------------------------------------------------------------- /tika-eval/src/main/resources/tika-eval-profiler-config.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/main/resources/tika-eval-profiler-config.xml -------------------------------------------------------------------------------- /tika-eval/src/test/java/org/apache/tika/MockDBWriter.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/test/java/org/apache/tika/MockDBWriter.java -------------------------------------------------------------------------------- /tika-eval/src/test/java/org/apache/tika/eval/TikaEvalCLITest.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/test/java/org/apache/tika/eval/TikaEvalCLITest.java -------------------------------------------------------------------------------- /tika-eval/src/test/resources/common_tokens/en: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/test/resources/common_tokens/en -------------------------------------------------------------------------------- /tika-eval/src/test/resources/common_tokens/es: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/test/resources/common_tokens/es -------------------------------------------------------------------------------- /tika-eval/src/test/resources/common_tokens/zh-cn: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/test/resources/common_tokens/zh-cn -------------------------------------------------------------------------------- /tika-eval/src/test/resources/common_tokens/zh-tw: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/test/resources/common_tokens/zh-tw -------------------------------------------------------------------------------- /tika-eval/src/test/resources/test-dirs/extractsA/file1.pdf.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/test/resources/test-dirs/extractsA/file1.pdf.json -------------------------------------------------------------------------------- /tika-eval/src/test/resources/test-dirs/extractsA/file10_permahang.txt.json: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /tika-eval/src/test/resources/test-dirs/extractsA/file11_oom.txt.json: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /tika-eval/src/test/resources/test-dirs/extractsA/file15_tags.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/test/resources/test-dirs/extractsA/file15_tags.json -------------------------------------------------------------------------------- /tika-eval/src/test/resources/test-dirs/extractsA/file5_emptyA.pdf.json: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /tika-eval/src/test/resources/test-dirs/extractsB/file1.pdf.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/test/resources/test-dirs/extractsB/file1.pdf.json -------------------------------------------------------------------------------- /tika-eval/src/test/resources/test-dirs/extractsB/file11_oom.txt.json: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /tika-eval/src/test/resources/test-dirs/extractsB/file15_tags.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/test/resources/test-dirs/extractsB/file15_tags.html -------------------------------------------------------------------------------- /tika-eval/src/test/resources/test-dirs/extractsB/file4_emptyB.pdf.json: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /tika-eval/src/test/resources/test-dirs/extractsB/file7_badJson.pdf.json: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /tika-eval/src/test/resources/test-dirs/raw_input/file1.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/test/resources/test-dirs/raw_input/file1.pdf -------------------------------------------------------------------------------- /tika-eval/src/test/resources/test-dirs/raw_input/file11_oom.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/test/resources/test-dirs/raw_input/file11_oom.txt -------------------------------------------------------------------------------- /tika-eval/src/test/resources/test-dirs/raw_input/file4_emptyB.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/test/resources/test-dirs/raw_input/file4_emptyB.pdf -------------------------------------------------------------------------------- /tika-eval/src/test/resources/test-dirs/raw_input/file5_emptyA.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/test/resources/test-dirs/raw_input/file5_emptyA.pdf -------------------------------------------------------------------------------- /tika-eval/src/test/resources/test-dirs/raw_input/file8_IOEx.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-eval/src/test/resources/test-dirs/raw_input/file8_IOEx.pdf -------------------------------------------------------------------------------- /tika-eval/src/test/resources/test-dirs/raw_input/file9_noextract.txt: -------------------------------------------------------------------------------- 1 | dummy file 2 | -------------------------------------------------------------------------------- /tika-example/pom.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-example/pom.xml -------------------------------------------------------------------------------- /tika-example/src/main/java/org/apache/tika/example/Language.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-example/src/main/java/org/apache/tika/example/Language.java -------------------------------------------------------------------------------- /tika-example/src/main/java/org/apache/tika/example/Pharmacy.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-example/src/main/java/org/apache/tika/example/Pharmacy.java -------------------------------------------------------------------------------- /tika-example/src/main/resources/org/apache/tika/example/test.doc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-example/src/main/resources/org/apache/tika/example/test.doc -------------------------------------------------------------------------------- /tika-example/src/main/resources/org/apache/tika/example/test2.doc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-example/src/main/resources/org/apache/tika/example/test2.doc -------------------------------------------------------------------------------- /tika-java7/pom.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-java7/pom.xml -------------------------------------------------------------------------------- /tika-java7/src/test/resources/test-documents/test.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-java7/src/test/resources/test-documents/test.html -------------------------------------------------------------------------------- /tika-langdetect/pom.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-langdetect/pom.xml -------------------------------------------------------------------------------- /tika-langdetect/src/test/resources/log4j.properties: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-langdetect/src/test/resources/log4j.properties -------------------------------------------------------------------------------- /tika-nlp/pom.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-nlp/pom.xml -------------------------------------------------------------------------------- /tika-parent/pom.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parent/pom.xml -------------------------------------------------------------------------------- /tika-parsers/.gitignore: -------------------------------------------------------------------------------- 1 | /.pydevproject 2 | -------------------------------------------------------------------------------- /tika-parsers/pom.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/pom.xml -------------------------------------------------------------------------------- /tika-parsers/src/main/appended-resources/META-INF/LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/main/appended-resources/META-INF/LICENSE -------------------------------------------------------------------------------- /tika-parsers/src/main/java/org/apache/tika/parser/dbf/DBFRow.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/main/java/org/apache/tika/parser/dbf/DBFRow.java -------------------------------------------------------------------------------- /tika-parsers/src/test/java/org/apache/tika/TestParsers.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/java/org/apache/tika/TestParsers.java -------------------------------------------------------------------------------- /tika-parsers/src/test/java/org/apache/tika/TestXXEInXML.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/java/org/apache/tika/TestXXEInXML.java -------------------------------------------------------------------------------- /tika-parsers/src/test/java/org/apache/tika/XMLTestBase.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/java/org/apache/tika/XMLTestBase.java -------------------------------------------------------------------------------- /tika-parsers/src/test/java/org/apache/tika/mime/MimeTypeTest.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/java/org/apache/tika/mime/MimeTypeTest.java -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/log4j.properties: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/log4j.properties -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/Doc1_ole.doc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/Doc1_ole.doc -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/EmbeddedPDF.docx: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/EmbeddedPDF.docx -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/MANIFEST.XML.TSD: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/MANIFEST.XML.TSD -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/NUTCH-1997.cbor: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/NUTCH-1997.cbor -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/NullHeader.docx: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/NullHeader.docx -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/TIKA-216.tgz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/TIKA-216.tgz -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/Test1.txt.tsd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/Test1.txt.tsd -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/Test2.txt.tsd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/Test2.txt.tsd -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/Test3.docx.tsd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/Test3.docx.tsd -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/Test4.pdf.tsd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/Test4.pdf.tsd -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/Test5.PNG.tsd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/Test5.PNG.tsd -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/Zamora2010.dif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/Zamora2010.dif -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/baseball.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/baseball.gif -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/baseball.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/baseball.jpg -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/baseball.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/baseball.png -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/big-preamble.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/big-preamble.html -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/boilerplate.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/boilerplate.html -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/chm/IMJPCL.CHM: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/chm/IMJPCL.CHM -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/chm/IMJPCLE.CHM: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/chm/IMJPCLE.CHM -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/chm/IMTCEN.CHM: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/chm/IMTCEN.CHM -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/chm/admin.chm: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/chm/admin.chm -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/chm/cmak_ops.CHM: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/chm/cmak_ops.CHM -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/chm/comexp.CHM: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/chm/comexp.CHM -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/chm/gpedit.CHM: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/chm/gpedit.CHM -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/chm/tcpip.CHM: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/chm/tcpip.CHM -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/chm/wmicontrol.CHM: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/chm/wmicontrol.CHM -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/complex.mbox: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/complex.mbox -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/droste.zip: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/droste.zip -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/english.cp500.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/english.cp500.txt -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/footnotes.docx: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/footnotes.docx -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/full_encrypted.7z: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/full_encrypted.7z -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/headerPic.docx: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/headerPic.docx -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/headers.mbox: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/headers.mbox -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/jxl.xls: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/jxl.xls -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/moby.zip: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/moby.zip -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/mock/example.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/mock/example.xml -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/mock/fake_oom.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/mock/fake_oom.xml -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/mock/real_oom.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/mock/real_oom.xml -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/mock/sleep.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/mock/sleep.xml -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/multi-language.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/multi-language.txt -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/multiline.mbox: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/multiline.mbox -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/pictures.ppt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/pictures.ppt -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/protect.xlsx: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/protect.xlsx -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/protectedFile.xlsx: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/protectedFile.xlsx -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/quine.gz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/quine.gz -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/quoted.mbox: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/quoted.mbox -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/resume.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/resume.html -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/rsstest_091.rss: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/rsstest_091.rss -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/rsstest_20.rss: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/rsstest_20.rss -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/russian.cp866.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/russian.cp866.txt -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/simple.mbox: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/simple.mbox -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/single_mail.mbox: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/single_mail.mbox -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/tableNames.numbers: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/tableNames.numbers -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/test-columnar.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/test-columnar.csv -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/test-columnar.ods: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/test-columnar.ods -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/test-columnar.xls: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/test-columnar.xls -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/test-columnar.xlsb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/test-columnar.xlsb -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/test-columnar.xlsx: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/test-columnar.xlsx -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/test-columnar.xpt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/test-columnar.xpt -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/test-documents.7z: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/test-documents.7z -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/test-documents.cab: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/test-documents.cab -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/test-documents.ddf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/test-documents.ddf -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/test-documents.dmg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/test-documents.dmg -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/test.doc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/test.doc -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/test.fb2: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/test.fb2 -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/test.hdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/test.hdf -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/test.he5: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/test.he5 -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/test1.swf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/test1.swf -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/test2.swf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/test2.swf -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/test3.swf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/test3.swf -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testACCESS.mdb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testACCESS.mdb -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testAFM.afm: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testAFM.afm -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testAIFF.aif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testAIFF.aif -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testAMR-WB.amr: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testAMR-WB.amr -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testAMR.amr: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testAMR.amr -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testAPK.apk: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testAPK.apk -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testARofSND.ar: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testARofSND.ar -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testARofText.ar: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testARofText.ar -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testASF.asf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testASF.asf -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testASiCE.asice: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testASiCE.asice -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testASiCS.asics: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testASiCS.asics -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testATOM.atom: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testATOM.atom -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testAU.au: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testAU.au -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testBAT.bat: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testBAT.bat -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testBIBTEX.bib: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testBIBTEX.bib -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testBMP.bmp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testBMP.bmp -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testBMPfp.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testBMPfp.txt -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testBPG.bpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testBPG.bpg -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testBPG_GEO.bpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testBPG_GEO.bpg -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testC.c: -------------------------------------------------------------------------------- 1 | #include 2 | 3 | int main () 4 | { 5 | printf ("Apache Tika!\n"); 6 | } 7 | -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testCADKEY.prt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testCADKEY.prt -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testCADKEY2.prt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testCADKEY2.prt -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testCOREL.shw: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testCOREL.shw -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testCPP.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testCPP.cpp -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testCSS.css: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testCSS.css -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testCSV.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testCSV.csv -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testChm.chm: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testChm.chm -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testChm2.chm: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testChm2.chm -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testChm3.chm: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testChm3.chm -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testChm_oom.chm: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testChm_oom.chm -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testComment.doc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testComment.doc -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testComment.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testComment.pdf -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testComment.ppt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testComment.ppt -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testComment.rtf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testComment.rtf -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testComment.xls: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testComment.xls -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testDBF.dbf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testDBF.dbf -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testDCX.dcx: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testDCX.dcx -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testDITA.dita: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testDITA.dita -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testDITA2.dita: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testDITA2.dita -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testDJVU.djvu: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testDJVU.djvu -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testDOTM.dotm: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testDOTM.dotm -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testDWF2010.dwf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testDWF2010.dwf -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testDWG2000.dwg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testDWG2000.dwg -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testDWG2004.dwg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testDWG2004.dwg -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testDWG2007.dwg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testDWG2007.dwg -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testDWG2010.dwg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testDWG2010.dwg -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testDigilite.fdf: -------------------------------------------------------------------------------- 1 |  D+ -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testEAR.ear: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testEAR.ear -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testEMF.emf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testEMF.emf -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testEMLX.emlx: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testEMLX.emlx -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testEPUB.epub: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testEPUB.epub -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testEXCEL.xls: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testEXCEL.xls -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testEXCEL.xlsb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testEXCEL.xlsb -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testEXCEL.xlsx: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testEXCEL.xlsx -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testEXCEL_4.xls: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testEXCEL_4.xls -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testEXCEL_5.xls: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testEXCEL_5.xls -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testFITS.fits: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testFITS.fits -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testFLAC.flac: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testFLAC.flac -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testFLAC.oga: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testFLAC.oga -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testFLV.flv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testFLV.flv -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testFOXMAIL.box: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testFOXMAIL.box -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testFooter.ods: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testFooter.ods -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testFooter.odt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testFooter.odt -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testGIF.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testGIF.gif -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testH.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testH.h -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testHEIF.heic: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testHEIF.heic -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testHFA.hfa: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testHFA.hfa -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testHTML.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testHTML.html -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testHWP-v5b.hwp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testHWP-v5b.hwp -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testHWP_3.0.hwp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testHWP_3.0.hwp -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testHWP_5.0.hwp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testHWP_5.0.hwp -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testICNS.icns: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testICNS.icns -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testINDD.indd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testINDD.indd -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testIPA.ipa: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testIPA.ipa -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testJAR.jar: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testJAR.jar -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testJAVA.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testJAVA.java -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testJBIG2.jb2: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testJBIG2.jb2 -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testJPEG.jp2: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testJPEG.jp2 -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testJPEG.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testJPEG.jpg -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testJS.js: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testJS.js -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testJS_HTML.js: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testJS_HTML.js -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testKML.kml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testKML.kml -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testKMZ.kmz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testKMZ.kmz -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testKeynote.key: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testKeynote.key -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testLZMA_oom: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testLZMA_oom -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testMATLAB.m: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testMATLAB.m -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testMID.mid: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testMID.mid -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testMIF.mif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testMIF.mif -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testMKV.mkv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testMKV.mkv -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testMP3i18n.mp3: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testMP3i18n.mp3 -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testMP4.m4a: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testMP4.m4a -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testMSG.msg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testMSG.msg -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testMSOwnerFile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testMSOwnerFile -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testMYSQL.MYD: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testMYSQL.MYD -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testMYSQL.MYI: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testMYSQL.MYI -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testMYSQL.frm: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testMYSQL.frm -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testNLS1.nls: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testNLS1.nls -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testNLS2.nls: -------------------------------------------------------------------------------- 1 | DCHg98 2 | -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testOCR.docx: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testOCR.docx -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testOCR.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testOCR.jpg -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testOCR.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testOCR.pdf -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testOCR.pptx: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testOCR.pptx -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testODTnotaZipFile.odt: -------------------------------------------------------------------------------- 1 | This is not a zip file! 2 | -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testOPUS.opus: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testOPUS.opus -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testOneNote.one: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testOneNote.one -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testPBM.pbm: -------------------------------------------------------------------------------- 1 | P1 2 | 1 1 3 | 0 -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testPCX.pcx: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testPCX.pcx -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testPDF.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testPDF.pdf -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testPDF_bom.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testPDF_bom.pdf -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testPGM.pgm: -------------------------------------------------------------------------------- 1 | P2 2 | 1 1 3 | 255 4 | 0 -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testPICT.pct: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testPICT.pct -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testPNG.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testPNG.png -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testPPM.ppm: -------------------------------------------------------------------------------- 1 | P3 2 | 1 1 3 | 255 4 | 0 0 0 -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testPPT.potm: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testPPT.potm -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testPPT.ppsm: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testPPT.ppsm -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testPPT.ppsx: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testPPT.ppsx -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testPPT.ppt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testPPT.ppt -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testPPT.pptm: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testPPT.pptm -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testPPT.pptx: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testPPT.pptx -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testPPT.thmx: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testPPT.thmx -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testPPT.xps: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testPPT.xps -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testPSD.psd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testPSD.psd -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testPSD2.psd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testPSD2.psd -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testPSD_xmp.psd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testPSD_xmp.psd -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testPST.pst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testPST.pst -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testPages.pages: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testPages.pages -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testQUATTRO.qpw: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testQUATTRO.qpw -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testQUATTRO.wb3: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testQUATTRO.wb3 -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testRDF.rdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testRDF.rdf -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testRFC822: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testRFC822 -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testRFC822-big: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testRFC822-big -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testRFC822_eml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testRFC822_eml -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testRTF.rtf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testRTF.rtf -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testRotated.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testRotated.png -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testSAS.sas: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testSAS.sas -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testSAS.sd2: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testSAS.sd2 -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testSAS.xpt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testSAS.xpt -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testSAS2.sas: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testSAS2.sas -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testSQLITE3.db: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testSQLITE3.db -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testSVG.svg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testSVG.svg -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testSVG.svgz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testSVG.svgz -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testSqlite3b.db: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testSqlite3b.db -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testStyles.odt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testStyles.odt -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testTEI.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testTEI.xml -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testTIFF.tif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testTIFF.tif -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testTXT.txt: -------------------------------------------------------------------------------- 1 | Test d'indexation de Txt 2 | http://www.apache.org 3 | -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testTXT.zlib: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testTXT.zlib -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testTXT.zlib0: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testTXT.zlib0 -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testTXT.zlib5: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testTXT.zlib5 -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testTXT.zlib9: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testTXT.zlib9 -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testTables.key: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testTables.key -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testTinyPE.exe: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testTinyPE.exe -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testVISIO.vsd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testVISIO.vsd -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testVISIO.vsdm: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testVISIO.vsdm -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testVISIO.vsdx: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testVISIO.vsdx -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testVISIO.vssm: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testVISIO.vssm -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testVISIO.vssx: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testVISIO.vssx -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testVISIO.vstm: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testVISIO.vstm -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testVISIO.vstx: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testVISIO.vstx -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testVORBIS.ogg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testVORBIS.ogg -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testWAR.war: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testWAR.war -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testWAV.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testWAV.wav -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testWEBM.webm: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testWEBM.webm -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testWEBP.webp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testWEBP.webp -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testWINMAIL.dat: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testWINMAIL.dat -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testWMA.wma: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testWMA.wma -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testWMF.wmf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testWMF.wmf -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testWMV.wmv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testWMV.wmv -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testWORD.doc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testWORD.doc -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testWORD.docx: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testWORD.docx -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testWORD6.doc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testWORD6.doc -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testWORKS.wps: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testWORKS.wps -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testWebVTT.vtt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testWebVTT.vtt -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testXDP.xdp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testXDP.xdp -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testXFDF.xfdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testXFDF.xfdf -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testXHTML.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testXHTML.html -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testXLIFF12.xlf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testXLIFF12.xlf -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testXLIFF12.xlz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testXLIFF12.xlz -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testXML.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testXML.xml -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testXML2.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testXML2.xml -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testXML3.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testXML3.xml -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testXMP.xmp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testXMP.xmp -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testXXE.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testXXE.xml -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testZSTD.zstd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testZSTD.zstd -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/testZ_oom.Z: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/testZ_oom.Z -------------------------------------------------------------------------------- /tika-parsers/src/test/resources/test-documents/tika434.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-parsers/src/test/resources/test-documents/tika434.html -------------------------------------------------------------------------------- /tika-serialization/pom.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-serialization/pom.xml -------------------------------------------------------------------------------- /tika-server/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-server/README.md -------------------------------------------------------------------------------- /tika-server/assembly.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-server/assembly.xml -------------------------------------------------------------------------------- /tika-server/bin/init.d/tika: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-server/bin/init.d/tika -------------------------------------------------------------------------------- /tika-server/bin/install_tika_service.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-server/bin/install_tika_service.sh -------------------------------------------------------------------------------- /tika-server/bin/tika: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-server/bin/tika -------------------------------------------------------------------------------- /tika-server/bin/tika.in.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-server/bin/tika.in.sh -------------------------------------------------------------------------------- /tika-server/pom.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-server/pom.xml -------------------------------------------------------------------------------- /tika-server/src/main/resources/log4j.properties: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-server/src/main/resources/log4j.properties -------------------------------------------------------------------------------- /tika-server/src/main/resources/tikaserver-template.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-server/src/main/resources/tikaserver-template.html -------------------------------------------------------------------------------- /tika-server/src/main/resources/tikaserver-version.properties: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /tika-server/src/test/resources/2exe.docx: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-server/src/test/resources/2exe.docx -------------------------------------------------------------------------------- /tika-server/src/test/resources/2pic.doc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-server/src/test/resources/2pic.doc -------------------------------------------------------------------------------- /tika-server/src/test/resources/2pic.docx: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-server/src/test/resources/2pic.docx -------------------------------------------------------------------------------- /tika-server/src/test/resources/CDEC_WEATHER_2010_03_02: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-server/src/test/resources/CDEC_WEATHER_2010_03_02 -------------------------------------------------------------------------------- /tika-server/src/test/resources/Doc1_ole.doc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-server/src/test/resources/Doc1_ole.doc -------------------------------------------------------------------------------- /tika-server/src/test/resources/english.txt: -------------------------------------------------------------------------------- 1 | This is English! 2 | -------------------------------------------------------------------------------- /tika-server/src/test/resources/foo.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-server/src/test/resources/foo.csv -------------------------------------------------------------------------------- /tika-server/src/test/resources/french.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-server/src/test/resources/french.txt -------------------------------------------------------------------------------- /tika-server/src/test/resources/log4j.properties: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-server/src/test/resources/log4j.properties -------------------------------------------------------------------------------- /tika-server/src/test/resources/logging/log4j_child.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-server/src/test/resources/logging/log4j_child.xml -------------------------------------------------------------------------------- /tika-server/src/test/resources/mock/fake_oom.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-server/src/test/resources/mock/fake_oom.xml -------------------------------------------------------------------------------- /tika-server/src/test/resources/mock/heavy_hang_100.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-server/src/test/resources/mock/heavy_hang_100.xml -------------------------------------------------------------------------------- /tika-server/src/test/resources/mock/heavy_hang_30000.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-server/src/test/resources/mock/heavy_hang_30000.xml -------------------------------------------------------------------------------- /tika-server/src/test/resources/mock/null_pointer.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-server/src/test/resources/mock/null_pointer.xml -------------------------------------------------------------------------------- /tika-server/src/test/resources/mock/real_oom.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-server/src/test/resources/mock/real_oom.xml -------------------------------------------------------------------------------- /tika-server/src/test/resources/mock/system_exit.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-server/src/test/resources/mock/system_exit.xml -------------------------------------------------------------------------------- /tika-server/src/test/resources/mock/testStaticStdOutErr.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-server/src/test/resources/mock/testStaticStdOutErr.xml -------------------------------------------------------------------------------- /tika-server/src/test/resources/mock/testStdOutErr.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-server/src/test/resources/mock/testStdOutErr.xml -------------------------------------------------------------------------------- /tika-server/src/test/resources/mock/thread_interrupt.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-server/src/test/resources/mock/thread_interrupt.xml -------------------------------------------------------------------------------- /tika-server/src/test/resources/password.xls: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-server/src/test/resources/password.xls -------------------------------------------------------------------------------- /tika-server/src/test/resources/pic.xls: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-server/src/test/resources/pic.xls -------------------------------------------------------------------------------- /tika-server/src/test/resources/pic.xlsx: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-server/src/test/resources/pic.xlsx -------------------------------------------------------------------------------- /tika-server/src/test/resources/test.doc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-server/src/test/resources/test.doc -------------------------------------------------------------------------------- /tika-server/src/test/resources/testDigilite.fdf: -------------------------------------------------------------------------------- 1 |  D+ -------------------------------------------------------------------------------- /tika-server/src/test/resources/testHTML.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-server/src/test/resources/testHTML.html -------------------------------------------------------------------------------- /tika-server/src/test/resources/testOCR.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-server/src/test/resources/testOCR.pdf -------------------------------------------------------------------------------- /tika-server/src/test/resources/testPDFTwoTextBoxes.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-server/src/test/resources/testPDFTwoTextBoxes.pdf -------------------------------------------------------------------------------- /tika-server/src/test/resources/testPassword4Spaces.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-server/src/test/resources/testPassword4Spaces.pdf -------------------------------------------------------------------------------- /tika-server/src/test/resources/testUnicodePassword.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-server/src/test/resources/testUnicodePassword.pdf -------------------------------------------------------------------------------- /tika-server/src/test/resources/test_recursive_embedded.docx: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-server/src/test/resources/test_recursive_embedded.docx -------------------------------------------------------------------------------- /tika-translate/pom.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-translate/pom.xml -------------------------------------------------------------------------------- /tika-xmp/pom.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-xmp/pom.xml -------------------------------------------------------------------------------- /tika-xmp/src/main/java/org/apache/tika/xmp/XMPMetadata.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-xmp/src/main/java/org/apache/tika/xmp/XMPMetadata.java -------------------------------------------------------------------------------- /tika-xmp/src/test/java/org/apache/tika/xmp/TikaToXMPTest.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlmatics/nlm-tika/HEAD/tika-xmp/src/test/java/org/apache/tika/xmp/TikaToXMPTest.java --------------------------------------------------------------------------------